CN116630500A - Virtual article generation method, virtual clothing generation method and electronic device - Google Patents
Virtual article generation method, virtual clothing generation method and electronic device Download PDFInfo
- Publication number
- CN116630500A CN116630500A CN202310530954.2A CN202310530954A CN116630500A CN 116630500 A CN116630500 A CN 116630500A CN 202310530954 A CN202310530954 A CN 202310530954A CN 116630500 A CN116630500 A CN 116630500A
- Authority
- CN
- China
- Prior art keywords
- target
- text
- dimensional model
- virtual
- texture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 115
- 238000009877 rendering Methods 0.000 claims abstract description 101
- 238000012986 modification Methods 0.000 claims description 26
- 230000004048 modification Effects 0.000 claims description 26
- 238000003860 storage Methods 0.000 claims description 24
- 238000009792 diffusion process Methods 0.000 claims description 14
- 230000003190 augmentative effect Effects 0.000 claims description 11
- 230000000694 effects Effects 0.000 abstract description 19
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 23
- 238000000605 extraction Methods 0.000 description 12
- 238000013507 mapping Methods 0.000 description 12
- 239000000463 material Substances 0.000 description 12
- 238000013461 design Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 229920000742 Cotton Polymers 0.000 description 5
- 210000001508 eye Anatomy 0.000 description 5
- 210000003128 head Anatomy 0.000 description 5
- 244000025254 Cannabis sativa Species 0.000 description 4
- 235000012766 Cannabis sativa ssp. sativa var. sativa Nutrition 0.000 description 4
- 235000012765 Cannabis sativa ssp. sativa var. spontanea Nutrition 0.000 description 4
- 235000009120 camo Nutrition 0.000 description 4
- 235000005607 chanvre indien Nutrition 0.000 description 4
- 239000011487 hemp Substances 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000010792 warming Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000251730 Chondrichthyes Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/16—Cloth
Landscapes
- Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The application discloses a virtual article generation method, a virtual clothes generation method and electronic equipment. The method comprises the following steps: acquiring first text data, wherein the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object. The virtual article generating method is applied to the fields of virtual fitting and three-dimensional reconstruction, and solves the technical problem that the generating effect of generating virtual articles in the related technology is poor.
Description
Technical Field
The application relates to the field of virtual fitting and three-dimensional reconstruction, in particular to a virtual article generation method, a virtual clothes generation method and electronic equipment.
Background
Aiming at the problems of more links, slow feedback, high labor cost and the like in the traditional clothing industry, a 3D clothing model can be quickly generated in an artificial intelligence AI mode at present, the clothing model can be worn on a 3D virtual model for observing wearing effects of 360 degrees, and the clothing wearing effects of the clothing on a real model or a user can be observed through AI real fit.
At present, the technology for generating the 3D clothing model requires a developer to design clothing manuscripts in advance, and corresponding virtual clothing can be generated by virtual design on the basis of the clothing manuscripts.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the application provides a virtual article generation method, a virtual clothes generation method and electronic equipment, which are used for at least solving the technical problem of poor generation effect of virtual articles in related technologies.
According to an aspect of an embodiment of the present application, there is provided a method for generating a virtual article, including: acquiring first text data, wherein the first text data at least comprises a first text for describing the type of a target virtual article and a second text for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object.
According to another aspect of the embodiment of the present application, there is also provided a method for generating a virtual article, including: responding to an input instruction acted on an operation interface, and displaying first text data on the operation interface, wherein the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; and responding to a rendering instruction acting on the operation interface, and displaying a target virtual object on the operation interface, wherein the target virtual object is generated by rendering a target three-dimensional model based on a first texture map, the first texture map is generated based on a second text and texture information corresponding to the target three-dimensional model, the target three-dimensional model is a model corresponding to the type of the target virtual object determined from a plurality of preset three-dimensional models based on the first text, and different preset three-dimensional models are used for representing different types of virtual objects.
According to another aspect of the embodiment of the present application, there is also provided a method for generating virtual clothes, including: capturing a first text describing the type of the target virtual clothes and a second text describing the texture of the target virtual clothes, wherein the virtual clothes are used for representing clothes rendered in a virtual environment; determining a target clothing model corresponding to the target virtual clothing from a plurality of preset clothing models based on the first text, wherein different preset clothing models are used for representing different types of virtual clothing; generating a first texture map corresponding to the target clothing model based on the second text and texture information corresponding to the target clothing model; rendering the target clothing model based on the first texture map, and generating the target virtual clothing.
According to another aspect of the embodiment of the present application, there is also provided a method for generating a virtual article, including: displaying first text data on a presentation screen of a Virtual Reality (VR) device or an Augmented Reality (AR) device, wherein the first text data at least comprises a first text for describing the type of a target virtual article and a second text for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in a virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object; the VR device or AR device is driven to present the target virtual article.
According to another aspect of the embodiment of the present application, there is also provided a method for generating a virtual article, including: acquiring first text data by calling a first interface, wherein the first interface comprises a first parameter, the parameter value of the first parameter is the first text data, the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object; and outputting the target virtual article by calling a second interface, wherein the second interface comprises a second parameter, and the parameter value of the second parameter is the target virtual article.
According to another aspect of the embodiment of the present application, there is also provided a virtual article generating apparatus, including: the system comprises an acquisition module, a rendering module and a rendering module, wherein the acquisition module is used for acquiring first text data, the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; the determining module is used for determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; the generating module is used for generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; and the rendering module is used for rendering the target three-dimensional model based on the first texture map and generating a target virtual article.
According to another aspect of the embodiment of the present application, there is also provided a virtual article generating apparatus, including: the first display module is used for responding to an input instruction acted on the operation interface, displaying first text data on the operation interface, wherein the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; the second display module is used for responding to a rendering instruction acting on the operation interface and displaying a target virtual object on the operation interface, wherein the target virtual object is generated by rendering a target three-dimensional model based on a first texture map, the first texture map is generated based on a second text and texture information corresponding to the target three-dimensional model, the target three-dimensional model is a model corresponding to the type of the target virtual object determined from a plurality of preset three-dimensional models based on the first text, and different preset three-dimensional models are used for representing different types of virtual objects.
According to another aspect of the embodiment of the present application, there is also provided a virtual clothes generating apparatus, including: the system comprises a capturing module, a rendering module and a rendering module, wherein the capturing module is used for capturing a first text describing the type of a target virtual dress and a second text describing the texture of the target virtual dress, wherein the virtual dress is used for representing the dress rendered in a virtual environment; the determining module is used for determining a target clothing model corresponding to the target virtual clothing from a plurality of preset clothing models based on the first text, wherein different preset clothing models are used for representing different types of virtual clothing; the generating module is used for generating a first texture map corresponding to the target clothing model based on the second text and texture information corresponding to the target clothing model; and the rendering module is used for rendering the target clothing model based on the first texture map and generating the target virtual clothing.
According to another aspect of the embodiment of the present application, there is also provided a virtual article generating apparatus, including: the virtual reality virtual environment rendering system comprises a first display module, a second display module and a rendering module, wherein the first display module is used for displaying first text data on a display screen of virtual reality VR equipment or augmented reality AR equipment, the first text data at least comprises a first text used for describing the type of a target virtual object and a second text used for describing the texture of the target virtual object, and the target virtual object is used for representing an object rendered in the virtual environment; the determining module is used for determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; the generating module is used for generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; the rendering module is used for rendering the target three-dimensional model based on the first texture map and generating a target virtual article; and the second display module is used for driving the VR equipment or the AR equipment to display the target virtual object.
According to another aspect of the embodiment of the present application, there is also provided a virtual article generating apparatus, including: the system comprises an acquisition module, a first interface and a rendering module, wherein the acquisition module is used for acquiring first text data by calling the first interface, the first interface comprises a first parameter, the parameter value of the first parameter is the first text data, the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; the determining module is used for determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; the generating module is used for generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; the rendering module is used for rendering the target three-dimensional model based on the first texture map and generating a target virtual article; and the output module is used for outputting the target virtual article by calling a second interface, wherein the second interface comprises a second parameter, and the parameter value of the second parameter is the target virtual article.
According to another aspect of the embodiment of the present application, there is also provided an electronic device, including: a memory storing an executable program; and a processor for running a program, wherein the program when run performs the method of any one of the above.
According to another aspect of the embodiments of the present application, there is also provided a computer readable storage medium, the computer readable storage medium including a stored executable program, wherein the computer readable storage medium is controlled to perform the method of any one of the above when the executable program is run.
In the embodiment of the application, first text data is acquired, wherein the first text data at least comprises a first text for describing the type of a target virtual object and a second text for describing the texture of the target virtual object, and the target virtual object is used for representing the object rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; and rendering the target three-dimensional model based on the first texture map to generate a target virtual object. It is easy to notice that, in the application, the common user can quickly and automatically generate the virtual article only by inputting simple text description, the common user does not need to design the virtual article by himself, the target three-dimensional model is obtained by screening a plurality of preset three-dimensional models, the resolution of the target three-dimensional model is higher, the texture map is generated based on texts, the resolution of the texture map is higher and is closer to the material of real clothing, the purpose of improving the generation effect of generating the virtual article is achieved, the technical effect of improving the generation effect of generating the virtual article is achieved, and the technical problem that the generation effect of generating the virtual article in the related technology is poor is solved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application, as claimed.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
fig. 1 is a schematic diagram of a hardware environment of a virtual reality device of a virtual article generation method according to an embodiment of the application;
FIG. 2 is a block diagram of a computing environment for a method of generating virtual articles according to an embodiment of the application;
FIG. 3 is a flow chart of a method of generating virtual articles according to embodiment 1 of the present application;
FIG. 4 is a schematic diagram of an alternative pre-set tiling method according to embodiment 1 of the present application;
FIG. 5 is a schematic diagram of an alternative three-dimensional virtual apparel generation method in accordance with embodiment 1 of the present application;
FIG. 6 is a flow chart of a method of generating virtual articles according to embodiment 2 of the present application;
FIG. 7 is a schematic diagram of an interface for an alternative virtual article generation method according to embodiment 2 of the present application;
FIG. 8 is a flowchart of a method of generating virtual apparel in accordance with embodiment 3 of the present application;
FIG. 9 is a flowchart of a method of generating a virtual article according to embodiment 4 of the present application;
FIG. 10 is a flowchart of a method of generating a virtual article according to embodiment 5 of the present application;
fig. 11 is a schematic diagram of a virtual article generating apparatus according to embodiment 1 of the present application;
fig. 12 is a schematic diagram of a virtual article generating apparatus according to embodiment 2 of the present application;
fig. 13 is a schematic view of a virtual clothes generating apparatus according to embodiment 3 of the present application;
fig. 14 is a schematic view of a virtual article generating apparatus according to embodiment 4 of the present application;
fig. 15 is a schematic view of a virtual article generating apparatus according to embodiment 5 of the present application;
fig. 16 is a block diagram of a computer terminal according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
First, partial terms or terminology appearing in the course of describing embodiments of the application are applicable to the following explanation:
CLIP: contrastive Language-Image Pre-Training, a pattern-text correlation matching model, which is used for extracting characters of a virtual article to obtain character features, extracting images of the virtual article to obtain Image features, and constructing a mapping relation between the character features and the corresponding Image features.
Diffuse: diffusion model, one of the commonly used generation models, is used to generate pictures.
primary: the prior knowledge, i.e. the knowledge verified in advance, can be understood as the mapping relation between the text features and the corresponding image features in this embodiment.
Mask: masks, which control the area or process of image processing by masking the image to be processed (either fully or partially) with a selected image, graphic or object.
Example 1
According to an embodiment of the present application, there is provided a method of generating virtual articles, it being noted that the steps shown in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that herein.
Fig. 1 is a schematic diagram of a hardware environment of a virtual reality device of a virtual article generating method according to an embodiment of the application. As shown in fig. 1, the virtual reality device 104 is connected to the terminal 106, the terminal 106 is connected to the server 102 via a network, and the virtual reality device 104 is not limited to: the terminal 104 is not limited to a PC, a mobile phone, a tablet computer, etc., and the server 102 may be a server corresponding to a media file operator, and the network includes, but is not limited to: a wide area network, a metropolitan area network, or a local area network.
Optionally, the virtual reality device 104 of this embodiment includes: memory, processor, and transmission means. The memory is used to store an application program that can be used to perform: acquiring first text data, wherein the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object, so that the technical problem that the generation effect of the generated virtual object in the related technology is poor is solved, and the purpose of improving the generation effect of the virtual object is achieved.
The terminal of the embodiment may be configured to perform presentation of first text data on a presentation screen of a Virtual Reality (VR) device or an augmented Reality (Augmented Reality, AR) device, where the first text data includes at least a first text for describing a type of a target Virtual object, and a second text for describing a texture of the target Virtual object, and the target Virtual object is used to represent an object rendered in a Virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object; the VR device or AR device is driven to present the target virtual article.
Optionally, the HMD (Head MountDisplay, head mounted display) head display and the eye tracking module of the virtual reality device 104 of this embodiment have the same functions as those of the above embodiment, that is, a screen in the HMD head display is used for displaying a real-time picture, and the eye tracking module in the HMD is used for acquiring a real-time motion track of an eyeball of a user. The terminal of the embodiment obtains the position information and the motion information of the user in the real three-dimensional space through the tracking system, and calculates the three-dimensional coordinates of the head of the user in the virtual three-dimensional space and the visual field orientation of the user in the virtual three-dimensional space.
The hardware architecture block diagram shown in fig. 1 may be used not only as an exemplary block diagram for an AR/VR device (or mobile device) as described above, but also as an exemplary block diagram for a server as described above, and in an alternative embodiment, fig. 2 shows in block diagram form one embodiment of a computing node in a computing environment 201 using an AR/VR device (or mobile device) as described above in fig. 1. Fig. 2 is a block diagram of a computing environment for a method of generating virtual articles according to an embodiment of the present application, as shown in fig. 2, the computing environment 201 includes a plurality of computing nodes (e.g., servers) running on a distributed network (shown as 210-1, 210-2, …). Different computing nodes contain local processing and memory resources and end user 202 may run applications or store data remotely in computing environment 201. The application may be provided as a plurality of services 220-1, 220-2, 220-3, and 220-4 in computing environment 201, representing services "A", "D", "E", and "H", respectively.
End user 202 may provide and access services through a web browser or other software application on a client, in some embodiments, provisioning and/or requests of end user 202 may be provided to portal gateway 230. Ingress gateway 230 may include a corresponding agent to handle provisioning and/or request for services (one or more services provided in computing environment 201).
Services are provided or deployed in accordance with various virtualization techniques supported by the computing environment 201. In some embodiments, services may be provided according to Virtual Machine (VM) based virtualization, container based virtualization, and/or the like. Virtual machine-based virtualization may be the emulation of a real computer by initializing a virtual machine, executing programs and applications without directly touching any real hardware resources. While the virtual machine virtualizes the machine, according to container-based virtualization, a container may be started to virtualize the entire Operating System (OS) so that multiple workloads may run on a single Operating System instance.
In one embodiment based on container virtualization, several containers of a service may be assembled into one Pod (e.g., kubernetes Pod). For example, as shown in FIG. 2, the service 220-2 may be equipped with one or more Pods 240-1, 240-2, …,240-N (collectively referred to as Pods). The Pod may include an agent 245 and one or more containers 242-1, 242-2, …,242-M (collectively referred to as containers). One or more containers in the Pod handle requests related to one or more corresponding functions of the service, and the agent 245 generally controls network functions related to the service, such as routing, load balancing, etc. Other services may also be equipped with similar Pod.
In operation, executing a user request from end user 202 may require invoking one or more services in computing environment 201, and executing one or more functions of one service may require invoking one or more functions of another service. As shown in FIG. 2, service "A"220-1 receives a user request of end user 202 from ingress gateway 230, service "A"220-1 may invoke service "D"220-2, and service "D"220-2 may request service "E"220-3 to perform one or more functions.
The computing environment may be a cloud computing environment, and the allocation of resources is managed by a cloud service provider, allowing the development of functions without considering the implementation, adjustment or expansion of the server. The computing environment allows developers to execute code that responds to events without building or maintaining a complex infrastructure. Instead of expanding a single hardware device to handle the potential load, the service may be partitioned to a set of functions that can be automatically scaled independently.
In the above-described operation environment, the present application provides a method for generating a virtual article as shown in fig. 3. It should be noted that, the method for generating a virtual article according to this embodiment may be performed by the mobile terminal according to the embodiment shown in fig. 1. Fig. 3 is a flowchart of a virtual article generation method according to embodiment 1 of the present application. As shown in fig. 3, the method may include the steps of:
Step S302, acquiring first text data, wherein the first text data at least comprises a first text for describing the type of a target virtual object and a second text for describing the texture of the target virtual object, and the target virtual object is used for representing the object rendered in the virtual environment.
In the technical solution provided in step S302 of the present application, the first text data may include: first text describing the type of the target virtual article may include, for example, but not limited to, "coat," "pants," "skirt," "coat," "dress"; and a second text describing the texture of the target virtual article, which may include, for example, but is not limited to, "color", "style", "pattern", "apparel material", "style". The target virtual object may be a virtual object that the user wants to obtain, where rendering the target virtual object in the virtual environment may be performed, and the target virtual object may include, but is not limited to: blouse, coat, shirt, short sleeve, jeans, leg-warming trousers, body skirt, dress, etc. The target virtual article may be a virtual article for use by a person in a captured video, or may be a virtual article in a role playing game, but is not limited thereto.
In an alternative embodiment, when the user wishes to reload a character in the captured video, first text data may be entered, where the first text data may include a first text describing the type of the target virtual article and a second text describing the texture of the target virtual article. For example, when a user wants to reload a character in a video, firstly, a piece of black long blouse which can keep out cold can be input, and secondly, based on text information input by the user, a first text "blouse" and a second text "black", "long blouse" can be extracted, and first text data can be obtained. For another example, when the user wants to reload the person in the video, firstly, a piece of white and dark-lined new Chinese dress for photographing can be input, and secondly, based on the text information input by the user, the first text "dress" and the second text "white", "dark-lined" and "new Chinese" can be extracted, so as to obtain the first text data. It should be noted that, the text input part has some preset text description for the user to refer to, and provides inspiration.
In another alternative embodiment, when the user needs to design the clothing of the virtual character in the role playing game, first text data may be input, where the first text data may describe the type of the target virtual article and describe the texture of the target virtual article. For example, when the user needs to design the skirt for the virtual character in the game, firstly, a color long skirt with classical elements in China and gorgeous silk material can be input, and secondly, based on the text information input by the user, a first text "long skirt" and a second text "color", "classical", "gorgeous silk material" can be extracted, and first text data can be obtained.
Step S304, determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects.
The preset three-dimensional model may be a plurality of three-dimensional models set in advance by a user and corresponding to types of the plurality of virtual articles. For example, may include, but is not limited to: a three-dimensional model of the type "coat", a three-dimensional model of the type "jacket", a three-dimensional model of the type "jeans", a three-dimensional model of the type "dress". The above-described target three-dimensional model may be a three-dimensional model corresponding to the type of the target virtual article, for example, when the target virtual article is "coat", the target three-dimensional model may be a three-dimensional model of "coat" set in advance, when the target virtual article is "leg-warming trousers", the target three-dimensional model may be a three-dimensional model of "leg-warming trousers" set in advance, and when the target virtual article is "skirt", the target three-dimensional model may be a three-dimensional model of "skirt" set in advance, but is not limited thereto.
In an alternative embodiment, after the first text is acquired, a target three-dimensional model corresponding to the type of the target virtual article may be determined from a plurality of preset three-dimensional models based on the first text. For example, when the first text is acquired as "blouse", the target three-dimensional model may be determined as a three-dimensional model of a preset "blouse", and when the first text is acquired as "shirt", the target three-dimensional model may be determined as a three-dimensional model of a preset "shirt", but is not limited thereto.
Step S306, based on the second text and texture information corresponding to the target three-dimensional model, a first texture map corresponding to the target three-dimensional model is generated.
The texture information corresponding to the target three-dimensional model may be initial texture information of the target three-dimensional model, and in this embodiment, the texture information may include, but is not limited to: texture map coordinates (also referred to as UV coordinates). The first texture map may be generated based on the target texture information of the target three-dimensional model, and the texture map corresponding to the target three-dimensional model may be, for example, but not limited to, a texture map capable of representing "color", "style", and the like of the target three-dimensional model. The first texture map may display target texture information, where the target texture information may be texture information corresponding to the target three-dimensional model, which is obtained based on the second text.
In an alternative embodiment, after determining the target three-dimensional model, the texture information of the target three-dimensional model may be modified based on the second text and the texture information corresponding to the target three-dimensional model, so as to obtain target texture information, and generate the first texture map corresponding to the target three-dimensional model based on the target texture information. For example, when the second text includes, but is not limited to: when the target three-dimensional model is purple, the body is shaped, the sun pattern is shaped, the gentlewoman wind is shaped, and the cotton and hemp materials are shaped, texture information in the target three-dimensional model can be updated based on the second text, and target texture information corresponding to the target three-dimensional model is obtained, wherein the target texture information can comprise but is not limited to: and secondly, generating a first texture map corresponding to the target three-dimensional model based on the target texture information, wherein the first texture map can display target texture information such as purple, slimming, sun pattern, gentlewoman wind, cotton and hemp material and the like.
And step 308, rendering the target three-dimensional model based on the first texture map to generate a target virtual article.
In an alternative embodiment, after the first texture map is obtained, the target three-dimensional model may be rendered based on the first texture map, and thus the target virtual article may be generated. For example, after obtaining the first texture map displaying texture information such as "purple", "build", "sun pattern", "gentlewoman wind", "cotton and hemp material", a target three-dimensional model of the type "shirt" may be rendered based on the first texture map, and further a shirt with purple color, build, sun pattern, style gentlewoman style, cotton and hemp material may be obtained.
In the embodiment of the application, first text data is acquired, wherein the first text data at least comprises a first text for describing the type of a target virtual object and a second text for describing the texture of the target virtual object, and the target virtual object is used for representing the object rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; and rendering the target three-dimensional model based on the first texture map to generate a target virtual object. It is easy to notice that, in the application, the common user can quickly and automatically generate the virtual article only by inputting simple text description, the common user does not need to design the virtual article by himself, the target three-dimensional model is obtained by screening a plurality of preset three-dimensional models, the resolution of the target three-dimensional model is higher, the texture map is generated based on texts, the resolution of the texture map is higher and is closer to the material of real clothing, the purpose of improving the generation effect of generating the virtual article is achieved, the technical effect of improving the generation effect of generating the virtual article is achieved, and the technical problem that the generation effect of generating the virtual article in the related technology is poor is solved.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.
In the above embodiment of the present application, based on the first text, determining, from a plurality of preset three-dimensional models, a target three-dimensional model corresponding to a type of a target virtual article includes: performing text recognition on the first text, and determining a target type; and acquiring a preset three-dimensional model corresponding to the type of the target virtual object from the plurality of preset three-dimensional models to obtain a target three-dimensional model.
The target type may be a type of the target virtual article obtained after text recognition is performed on the first text.
In an alternative embodiment, after receiving the first text input by the user, the first text may be first text-identified to obtain the target type, and since the user typically inputs a complete first text data, the first text data may also be text-identified to obtain the target type. And secondly, determining a preset three-dimensional model with the type corresponding to the target type from a plurality of preset three-dimensional models, and further obtaining the target three-dimensional model.
In the above embodiment of the present application, generating a first texture map corresponding to a target three-dimensional model based on texture information corresponding to a second text and the target three-dimensional model includes: tiling the target three-dimensional model according to a preset tiling method to obtain texture information; extracting features of the first text data to obtain first text features; extracting priori knowledge from the first text features to generate first image features; and performing feature decoding on the first image features based on the texture information by using the diffusion model to generate a first texture map.
The preset tiling method may be a method of tiling the first region and the second region of the target three-dimensional model on the front side and tiling the back side after the first region and the second region are spliced, and in this embodiment, the preset tiling method may be referred to as a special UV typesetting method, but is not limited thereto. The preset tiling method can enable the diffusion model to have semantic information, and can ensure that reasonable clothing mapping can be directly generated while image features are mapped to the target three-dimensional model. Wherein the first region may be a subject region of the target three-dimensional model. The second region may be a peripheral region of the target three-dimensional model. Fig. 4 is a schematic diagram of an alternative preset tiling method according to embodiment 1 of the present application, as shown in fig. 4, when the target three-dimensional model is a jacket, the first region may be a torso region of the jacket, and the second region may be sleeve regions of the jacket, so that the preset tiling method may be tiling the torso region and sleeve regions of the jacket on the front side after they are spliced, and tiling the torso region and sleeve regions of the jacket on the back side after they are spliced. The first text feature may be a text feature obtained by extracting a feature from the first text data. The first image feature may be an image feature corresponding to the first text feature, which is obtained by extracting a priori knowledge. The Diffusion model described above may be a Diffusion model, but is not limited thereto.
In an alternative embodiment, firstly, tiling operation can be performed on the target three-dimensional model according to a preset tiling method to obtain texture information of the target three-dimensional model, secondly, feature extraction can be performed on first text data through CLIP to obtain first text features, priori knowledge extraction can be performed on the first text to obtain first image features corresponding to the first text, and finally feature decoding can be performed on the first image features based on the texture information through a diffusion model to generate a first texture map.
In the above embodiment of the present application, acquiring the first text data includes: acquiring an article image obtained by shooting an entity article in a real environment; generating original text data based on the object image, wherein the original text data at least comprises text for describing the type of the entity object and text for describing the texture of the entity object; outputting original text data; and under the condition that the modification instruction is received, modifying the original text data based on the modification instruction to obtain the first text data.
The physical items described above may include, but are not limited to: a real shirt, a real jacket, a real jeans, a real skirt. The original text data may include: text describing the type of the physical object, and text describing the texture of the physical object. The modification instructions described above may be user-entered instructions for modifying the type and texture of the item image.
In an alternative embodiment, firstly, shooting a physical object in a real environment through a user terminal to obtain an object image; secondly, extracting features of the object image through the CLIP to obtain original text data; the original text data may then be output to the user; finally, when the user modifies the original text data, a modification instruction is input, and after the modification instruction is received, the original text data can be modified based on the modification instruction, so that the first text data can be obtained. For example, if a user looks at a piece of designed sweater, and wants to generate a virtual sweater containing similar design elements, the user can shoot the sweater in the real environment through a mobile terminal (for example, a camera) to obtain a sweater image, upload the sweater image, then map the picture back to text through a reverse encoder (encoder) and a decoder (decoder) of the CLIP, that is, can extract features of the sweater image through the encoder and the decoder to obtain original text data of the sweater, for example, data such as "sweater", "white", "loose", "shark pattern", "pure cotton material" and the like, and then output the original text data to the user, and the user can customize and modify the original text data, for example, when the "loose" is required to be modified to be "normal", a modification instruction is issued, and then the "loose" in the original text data can be modified to be "normal" based on the modification instruction, so that the first text data can be obtained.
In the above embodiment of the present application, generating original text data based on an article image includes: extracting features of the object image to obtain second image features; extracting priori knowledge from the second image features to generate second text features; and performing feature decoding on the second text feature to generate original text data.
The second image feature may be an image feature of the article image obtained by extracting a feature of the article image. The second text feature may be a text feature corresponding to the second image feature, which is extracted by a priori knowledge.
In an alternative embodiment, feature extraction may be performed on the object image through CLIP to obtain a second image feature, priori knowledge extraction may be performed on the second image feature to obtain a second text feature corresponding to the second image feature, and finally decoding may be performed on the second text feature through CLIP to obtain the original text data.
In the above embodiment of the present application, after generating the first texture map corresponding to the target three-dimensional model based on the texture information corresponding to the target three-dimensional model and the second text, the method further includes: outputting a first texture map; obtaining a feedback texture map, wherein the feedback texture map is a texture map obtained by modifying a partial region in the first texture map; rendering the target three-dimensional model based on the feedback texture map to generate a target virtual object.
In an alternative embodiment, after the first texture map is obtained, if the user needs to modify the first texture map, a partial area in the first texture map may be modified through a mask (mask) to obtain a feedback texture map, and then the target three-dimensional model may be rendered through the feedback texture map to generate the target virtual object.
In an alternative embodiment, the user may continue to input results into the model for optimization and modification for the resulting unsatisfactory garment texture. The pattern may be globally modified; the area to be modified can also be modified locally by selecting the mask, adding a logo locally or removing unwanted patterns.
In the above embodiment of the present application, after generating the first texture map corresponding to the target three-dimensional model based on the first text data, the method further includes: outputting a first texture map; acquiring second text data, wherein the second text data is text data obtained by modifying the first text data based on the first texture map; generating a second texture map corresponding to the target three-dimensional model based on the second text data and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the second texture map to generate a target virtual object.
In an alternative embodiment, after the first texture map is obtained, if the user wants to modify the first texture map, the user may further modify the first text data based on the first texture map to obtain second text data, then may obtain the second text data, modify the texture information of the target three-dimensional model based on the second text data and the texture information corresponding to the target three-dimensional model to obtain target texture information, generate a second texture map corresponding to the target three-dimensional model based on the target texture information, and finally may render the target three-dimensional model based on the second texture map to generate the target virtual article.
In the above embodiment of the present application, the method further includes: outputting at least one recommendation type and at least one recommendation color; determining a target recommendation type selected from the at least one recommendation type and a target recommendation color selected from the at least one recommendation color; generating a third texture map corresponding to the target three-dimensional model based on the first text data, the target recommended color and texture information corresponding to the target three-dimensional model; rendering the three-dimensional model corresponding to the target recommendation type based on the third texture map, and generating the target virtual object.
The target recommendation type may be a user-determined type, and the target recommendation color may be a user-determined color.
In an alternative embodiment, the method further comprises: outputting at least one recommended type and at least one recommended color to a user, for example, recommended types such as ' blouse ', ' coat ', ' shirt ', ' sweater ', ' and the like and recommended colors such as ' purple ', ' white ', ' black ', ' blue ' can be output to the user, then the texture information of the target three-dimensional model can be modified based on the first text data, the target recommended color and the texture information of the target three-dimensional model to obtain target texture information, then a third texture map corresponding to the target three-dimensional model can be generated based on the target texture information, and finally the target three-dimensional model corresponding to the target recommended type can be rendered based on the third texture map to generate the target virtual article.
In an alternative embodiment, fig. 5 is a schematic diagram of an alternative three-dimensional virtual clothes generating method according to embodiment 1 of the present application, as shown in fig. 5, according to the description input by the user, the expression of the clothes, such as "sweater", "semi-skirt", "one-dress", etc., may be first extracted, and matched with a preset version library, a target three-dimensional model corresponding to text data is found, and the target three-dimensional model is expanded according to a preset tiling method, then text description may be subjected to text encoding (text coder) to obtain text features, then prior knowledge (prior) is applied to the text features to extract image features corresponding to the text features, and then the image features are decoded (decoder) through a diffusion model to generate a texture map with textures, and finally the texture map and a 3D clothing model (i.e., the target three-dimensional model) may be matched.
It should be noted that the application has the advantages of real-time and fast, and can map onto the 3D model in real time when the 2D pattern is generated, thereby facilitating the observation effect of the user. Compared with the long link from design to printing to production in the past, the efficiency is greatly improved.
In addition, as the 3D model is directly generated by the diffusion model, the resolution is not high, and therefore the application uses the preset 3D model for replacement, only the control map is needed, and the controllability is higher. In addition, because the common diffusion model can not be directly used for generating the texture map, the application not only carries out targeted training on the model to ensure that the generated texture is more similar to the material of real clothing; in addition, the application adopts a special typesetting method to enable the image characteristics to have semantic information, so that the reasonable clothing map can be directly generated while the image characteristics are mapped back to 3D.
The application is based on the text-to-graph generating capability of the diffusion model, and the yield is superior to that of the 3D garment model of other related technologies, and the text inspiration provided by the application provides the flow of text-to-graph and graph-to-3D model, thereby providing an automatic digital solution and greatly shortening the cycle of garment design yield.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus a necessary general hardware platform, but that it may also be implemented by means of hardware. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present application.
Example 2
According to an embodiment of the present application, there is also provided a method of generating a virtual article, it being noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in an order other than that shown or described herein.
Fig. 6 is a flowchart of a virtual article generation method according to embodiment 2 of the present application. As shown in fig. 6, the method may include the steps of:
step S602, in response to an input instruction acting on an operation interface, displaying first text data on the operation interface, wherein the first text data at least comprises a first text for describing the type of a target virtual article and a second text for describing the texture of the target virtual article, and the target virtual article is used for representing an article rendered in a virtual environment;
in step S604, in response to a rendering instruction acting on the operation interface, displaying a target virtual object on the operation interface, where the target virtual object is generated by rendering a target three-dimensional model based on a first texture map, the first texture map is generated based on a second text and texture information corresponding to the target three-dimensional model, the target three-dimensional model is a model corresponding to a type of the target virtual object determined from a plurality of preset three-dimensional models based on the first text, and different preset three-dimensional models are used for characterizing different types of virtual objects.
Fig. 7 is a schematic diagram of an operation interface of an alternative virtual article generating method according to embodiment 2 of the present application, and as shown in fig. 7, the operation interface includes: an input instruction input area, a rendering instruction input area, and a display area. When a user inputs an input instruction in an input instruction input area on an operation interface, the operation interface can display first text data in a display area, wherein the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing an article rendered in a virtual environment; and secondly, after a rendering instruction is input in a rendering instruction input area of the user operation interface, the operation interface can display a target virtual object in a display area, wherein the target virtual object is generated by rendering a target three-dimensional model based on a first texture map, the first texture map is generated based on a second text and texture information corresponding to the target three-dimensional model, the target three-dimensional model is a model corresponding to the type of the target virtual object determined from a plurality of preset three-dimensional models based on the first text, and different preset three-dimensional models are used for representing different types of virtual objects.
In the above embodiment of the present application, the method further includes: responding to an uploading instruction acted on an operation interface, and displaying an article image on the operation interface, wherein the article image is obtained by shooting an entity article in a real environment; displaying original text data on an operation interface, wherein the original text data is generated based on an article image, and the original text data at least comprises a text for describing the type of the entity article and a text for describing the texture of the entity article; and responding to the modification instruction acted on the operation interface, and displaying first text data on the operation interface, wherein the first text data is obtained by modifying the original text data based on the modification instruction.
In an optional embodiment, after the user inputs the uploading instruction on the operation interface, the operation interface may display an article image in the display area, where the article image is obtained by shooting a physical article in the real environment; and the operation interface may display original text data in a display area, wherein the original text data is generated based on the item image, and the original text data includes at least text for describing a type of the physical item and text for describing a texture of the physical item; when the user inputs a modification instruction on the operation interface, the operation interface may display first text data in a display area, where the first text data is obtained by modifying original text data based on the modification instruction.
In the above embodiment of the present application, the method further includes: displaying a first texture map on an operation interface; responding to a first feedback instruction acting on the operation interface, and displaying a feedback texture map on the operation interface, wherein the feedback texture map is a texture map obtained by modifying a part of areas in the first texture map based on the first feedback instruction; and displaying the target virtual object on the operation interface, wherein the target virtual object is generated by rendering the target three-dimensional model based on the feedback texture map.
In an alternative embodiment, the operation interface may display a first texture map in the display area, and after the user inputs the first feedback instruction on the operation interface, the operation interface may display a feedback texture map in the display area, where the feedback texture map is a texture map obtained by modifying a part of the area in the first texture map based on the first feedback instruction; and based on the feedback texture map, the operation interface may display the target virtual object in the display area, wherein the target virtual object is generated by rendering the target three-dimensional model based on the feedback texture map.
In the above embodiment of the present application, the method further includes: displaying a first texture map on an operation interface; responding to a second feedback instruction acted on the operation interface, and displaying second text data on the operation interface, wherein the second text data is text data obtained by modifying the first text data based on the second feedback instruction; and displaying the target virtual object on the operation interface, wherein the target virtual object is generated by rendering the target three-dimensional model based on a second texture map, and the second texture map is generated based on the second text data and texture information corresponding to the target three-dimensional model.
In an alternative embodiment, the operation interface may display a first texture map in the display area, and after the user inputs a second feedback instruction on the operation interface, the operation interface may display second text data in the display area, where the second text data is text data obtained by modifying the first text data based on the second feedback instruction, and based on the second text data, the operation interface may display a target virtual object in the display area, where the target virtual object is generated by rendering the target three-dimensional model based on the second texture map, and the second texture map is generated based on the second text data and texture information corresponding to the target three-dimensional model.
In the above embodiment of the present application, the method further includes: displaying at least one recommendation type and at least one recommendation color on the operation interface; responding to a first selection instruction acting on at least one recommendation type and a second selection instruction acting on at least one recommendation color, displaying a target recommendation type corresponding to the first selection instruction in an operation interface, and displaying a target recommendation color corresponding to the second selection instruction; and displaying the target virtual object on the operation interface, wherein the target virtual object is generated by rendering the three-dimensional model corresponding to the target recommendation type based on a third texture map, and the third texture map is generated based on the first text data, the target recommendation color and texture information corresponding to the target three-dimensional model.
In an alternative embodiment, the operation interface may display at least one recommendation type and at least one recommendation color in the display area, after the user inputs a first selection instruction for selecting a target recommendation type and a second selection instruction for selecting a target recommendation color, the operation interface may display the target recommendation type corresponding to the first selection instruction in the display area and display the target recommendation color corresponding to the second selection instruction, and then the operation interface may display the target virtual object in the display area, where the target virtual object is generated by rendering a three-dimensional model corresponding to the target recommendation type based on a third texture map, and the third texture map is generated based on the first text data, the target recommendation color, and texture information corresponding to the target three-dimensional model.
Example 3
In accordance with an embodiment of the present application, there is also provided a method of generating virtual apparel, it being noted that the steps shown in the flowchart of the figures may be performed in a computer system, such as a set of computer-executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order other than that shown or described herein.
Fig. 8 is a flowchart of a virtual clothes generation method according to embodiment 3 of the present application. As shown in fig. 8, the method may include the steps of:
step S802, capturing a first text describing the type of the target virtual clothes and a second text describing the texture of the target virtual clothes, wherein the virtual clothes are used for representing clothes rendered in a virtual environment;
step S804, determining a target clothing model corresponding to the target virtual clothing from a plurality of preset clothing models based on the first text, wherein different preset clothing models are used for representing different types of virtual clothing;
step S806, generating a first texture map corresponding to the target clothing model based on the second text and texture information corresponding to the target clothing model;
step S808, rendering the target clothing model based on the first texture map, and generating the target virtual clothing.
The virtual apparel described above may be apparel rendered in a virtual environment, and may include, but is not limited to: "sweater", "pants". The preset virtual apparel may be various types of virtual apparel, and may include, but is not limited to: "coat", "under", "shirt", "dress". The target virtual dress may be a virtual dress required by the user.
In an alternative embodiment, first a first text describing the type of the target virtual garment and a second text describing the texture of the target virtual garment may be captured, wherein the virtual garment is used to characterize the garment rendered in the virtual environment; secondly, determining a target clothing model corresponding to the target virtual clothing from a plurality of preset clothing models based on the first text, wherein different preset clothing models are used for representing different types of virtual clothing; then, a first texture map corresponding to the target clothing model can be generated based on the second text and texture information corresponding to the target clothing model; and finally, rendering the target clothing model based on the first texture map to generate the target virtual clothing.
Example 4
There is also provided, in accordance with an embodiment of the present application, a method of generating a virtual article that may be applied in a virtual reality scenario, such as a virtual reality VR device, an augmented reality AR device, etc., it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system, such as a set of computer executable instructions, and, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order other than that illustrated herein.
Fig. 9 is a flowchart of a virtual article generation method according to embodiment 4 of the present application. As shown in fig. 9, the method may include the steps of:
step S902, first text data is displayed on a display screen of a Virtual Reality (VR) device or an Augmented Reality (AR) device, wherein the first text data at least comprises a first text for describing the type of a target virtual object and a second text for describing the texture of the target virtual object, and the target virtual object is used for representing the object rendered in the virtual environment;
step S904, determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects;
step S906, generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model;
step S908, rendering the target three-dimensional model based on the first texture map to generate a target virtual object;
in step S9010, the VR device or the AR device is driven to display the target virtual object.
In an alternative embodiment, first text data may be presented on a presentation screen of a virtual reality VR device or an augmented reality AR device, where the first text data includes at least a first text describing a type of a target virtual object and a second text describing a texture of the target virtual object, and the target virtual object is used to characterize an object rendered in a virtual environment; secondly, determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; then, a first texture map corresponding to the target three-dimensional model can be generated based on texture information corresponding to the second text and the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual article; finally, the VR device or the AR device can be driven to display the target virtual object.
Alternatively, in the present embodiment, the method for generating a virtual article described above may be applied to a hardware environment configured by a server and a virtual reality device. The virtual article is shown on a presentation screen of the virtual reality VR device or the augmented reality AR device, and the server may be a server corresponding to a media file operator, where the network includes but is not limited to: the virtual reality device is not limited to a wide area network, a metropolitan area network, or a local area network: virtual reality helmets, virtual reality glasses, virtual reality all-in-one machines, and the like.
Optionally, the virtual reality device comprises: memory, processor, and transmission means. The memory is used to store an application program that can be used to perform: acquiring first text data, wherein the first text data at least comprises a first text for describing the type of a target virtual article and a second text for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object.
It should be noted that, the method for generating the virtual object applied to the VR device or the AR device in this embodiment may include the method of the embodiment shown in fig. 3, so as to achieve the purpose of driving the VR device or the AR device to display the virtual object.
Alternatively, the processor of this embodiment may call the application program stored in the memory through the transmission device to perform the above steps. The transmission device can receive the media file sent by the server through the network and can also be used for data transmission between the processor and the memory.
Optionally, in the virtual reality device, a head-mounted display with eye tracking is provided, a screen in the head-mounted display of the HMD is used for displaying a video picture displayed, an eye tracking module in the HMD is used for acquiring real-time motion tracks of eyes of the user, a tracking system is used for tracking position information and motion information of the user in a real three-dimensional space, a calculation processing unit is used for acquiring real-time position and motion information of the user from the tracking system, and calculating three-dimensional coordinates of the head of the user in the virtual three-dimensional space, visual field orientation of the user in the virtual three-dimensional space and the like.
In the embodiment of the present application, the virtual reality device may be connected to a terminal, where the terminal and the server are connected through a network, and the virtual reality device is not limited to: the terminal is not limited to a PC, a mobile phone, a tablet PC, etc., and the server may be a server corresponding to a media file operator, and the network includes but is not limited to: a wide area network, a metropolitan area network, or a local area network.
Example 5
According to an embodiment of the present application, there is also provided a method of generating a virtual article, it being noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in an order other than that shown or described herein.
Fig. 10 is a flowchart of a virtual article generation method according to embodiment 5 of the present application. As shown in fig. 10, the method may include the steps of:
step S1002, acquiring first text data by calling a first interface, wherein the first interface comprises a first parameter, the parameter value of the first parameter is the first text data, the first text data at least comprises a first text used for describing the type of a target virtual object and a second text used for describing the texture of the target virtual object, and the target virtual object is used for representing the object rendered in the virtual environment;
step S1004, determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects;
Step S1006, generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model;
step S1008, rendering the target three-dimensional model based on the first texture map to generate a target virtual object;
in step S10010, the target virtual object is output by calling the second interface, where the second interface includes a second parameter, and a parameter value of the second parameter is the target virtual object.
The first interface may be an interface for acquiring the first text data from the server, and the second interface may be an interface for outputting the target virtual article to the server.
In an alternative embodiment, first text data may be acquired by calling a first interface, where the first interface includes a first parameter, and a parameter value of the first parameter is the first text data, where the first text data includes at least a first text for describing a type of a target virtual object, and a second text for describing a texture of the target virtual object, where the target virtual object is used to characterize an object rendered in a virtual environment; secondly, determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; then, a first texture map corresponding to the target three-dimensional model can be generated based on texture information corresponding to the second text and the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual article; and finally, the target virtual article can be output by calling a second interface, wherein the second interface comprises a second parameter, and the parameter value of the second parameter is the target virtual article.
Example 6
According to an embodiment of the present application, there is further provided a virtual article generating apparatus for implementing the virtual article generating method described above, and fig. 11 is a schematic diagram of a virtual article generating apparatus according to embodiment 1 of the present application, as shown in fig. 11, including: an acquisition module 1102, a determination module 1104, a generation module 1106, and a rendering module 1108.
The acquisition module is used for acquiring first text data, wherein the first text data at least comprises a first text used for describing the type of a target virtual object and a second text used for describing the texture of the target virtual object, and the target virtual object is used for representing the object rendered in the virtual environment; the determining module is used for determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; the generating module is used for generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; the rendering module is used for rendering the target three-dimensional model based on the first texture map and generating a target virtual object.
It should be noted that, the above-mentioned obtaining module 1102, determining module 1104, generating module 1106 and rendering module 1108 correspond to steps S302 to S308 in embodiment 1, and the four modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to those disclosed in embodiment 1 above. It should be noted that the above modules or units may be hardware components or software components stored in a memory and processed by one or more processors, or the above modules may also be part of an apparatus and may be run in the AR/VR device provided in embodiment 1.
In the above embodiment of the present application, the determining module includes: an identification unit and a first acquisition unit.
The recognition unit is used for recognizing the first text and determining the target type; the first acquisition unit is used for acquiring a preset three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models to obtain the target three-dimensional model.
In the above embodiment of the present application, the generating module includes: tiling unit, feature extraction unit, priori knowledge extraction unit and feature decoding unit.
The tiling unit is used for tiling the target three-dimensional model according to a preset tiling method to obtain texture information; the feature extraction unit is used for extracting features of the first text data to obtain first text features; the priori knowledge extraction unit is used for extracting the priori knowledge of the first text feature to generate a first image feature; the feature decoding unit is used for performing feature decoding on the first image features based on texture information by using the diffusion model to generate a first texture map.
In the above embodiment of the present application, the obtaining module includes: the device comprises a second acquisition unit, a first generation unit, a first output unit and a modification unit.
The second acquisition unit is used for acquiring an article image obtained by shooting an entity article in the real environment; the first generation unit is used for generating original text data based on the object image, wherein the original text data at least comprises a text for describing the type of the entity object and a text for describing the texture of the entity object; the first output unit is used for outputting original text data; the modification unit is used for modifying the original text data based on the modification instruction under the condition that the modification instruction is received, so as to obtain first text data.
In the above embodiment of the present application, the first generating unit includes: a first extraction subunit, a second extraction subunit, and a decoding subunit.
The first extraction subunit is used for extracting features of the object image to obtain second image features; the second extraction subunit is used for extracting priori knowledge of the second image features to generate second text features; the decoding subunit is used for performing feature decoding on the second text feature to generate original text data.
In the above embodiment of the present application, the generating module further includes: and a second output unit and a first rendering unit.
The second output unit is used for outputting the first texture mapping; obtaining a feedback texture map, wherein the feedback texture map is a texture map obtained by modifying a partial region in the first texture map; the first rendering unit is used for rendering the target three-dimensional model based on the feedback texture map and generating a target virtual article.
In the above embodiment of the present application, the generating module further includes: a third output unit, a second generation unit, and a second rendering unit.
The third output unit is used for outputting the first texture mapping; acquiring second text data, wherein the second text data is text data obtained by modifying the first text data based on the first texture map; the second generation unit is used for generating a second texture map corresponding to the target three-dimensional model based on the second text data and texture information corresponding to the target three-dimensional model; the second rendering unit is used for rendering the target three-dimensional model based on the second texture map and generating a target virtual object.
In the above embodiment of the present application, the apparatus further includes: the system comprises an output module, a recommendation determining module, a map generating module and a model rendering module.
The output module is used for outputting at least one recommendation type and at least one recommendation color; the recommendation determining module is used for determining a target recommendation type selected from at least one recommendation type and a target recommendation color selected from at least one recommendation color; the map generation module is used for generating a third texture map corresponding to the target three-dimensional model based on the first text data, the target recommended color and texture information corresponding to the target three-dimensional model; the model rendering module is used for rendering the three-dimensional model corresponding to the target recommendation type based on the third texture map, and generating the target virtual object.
Example 7
According to an embodiment of the present application, there is further provided a virtual article generating apparatus for implementing the virtual article generating method described above, and fig. 12 is a schematic diagram of a virtual article generating apparatus according to embodiment 2 of the present application, as shown in fig. 12, including: a first display module 1202 and a second display module 1204.
The first display module is used for responding to an input instruction acted on the operation interface, displaying first text data on the operation interface, wherein the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; the second display module is used for responding to a rendering instruction acting on the operation interface and displaying a target virtual object on the operation interface, wherein the target virtual object is generated by rendering a target three-dimensional model based on a first texture map, the first texture map is generated based on a second text and texture information corresponding to the target three-dimensional model, the target three-dimensional model is a model corresponding to the type of the target virtual object determined from a plurality of preset three-dimensional models based on the first text, and different preset three-dimensional models are used for representing different types of virtual objects.
Here, it should be noted that the first display module 1202 and the second display module 1204 correspond to steps S602 to S604 in embodiment 2, and the two modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to those disclosed in embodiment 1. It should be noted that the above modules or units may be hardware components or software components stored in a memory and processed by one or more processors, or the above modules may also be part of an apparatus and may be run in the AR/VR device provided in embodiment 1.
In the above embodiment of the present application, the apparatus further includes: the system comprises an article image display module, a first text data display module and a second text data display module.
The article image display module is used for responding to an uploading instruction acted on the operation interface and displaying an article image on the operation interface, wherein the article image is obtained by shooting an entity article in a real environment; the first text data display module is used for displaying original text data on the operation interface, wherein the original text data is generated based on the object image, and the original text data at least comprises text for describing the type of the entity object and text for describing the texture of the entity object; the second text data display module is used for responding to the modification instruction acted on the operation interface and displaying the first text data on the operation interface, wherein the first text data is obtained by modifying the original text data based on the modification instruction.
In the above embodiment of the present application, the apparatus further includes: the system comprises a first mapping display module, a second mapping display module and a first virtual article display module.
The first mapping display module is used for displaying a first texture mapping on the operation interface; the second map display module is used for responding to a first feedback instruction acting on the operation interface and displaying a feedback texture map on the operation interface, wherein the feedback texture map is a texture map obtained by modifying a part of areas in the first texture map based on the first feedback instruction; the first virtual article display module is used for displaying a target virtual article on the operation interface, wherein the target virtual article is generated by rendering the target three-dimensional model based on the feedback texture map.
In the above embodiment of the present application, the apparatus further includes: the system comprises a third mapping display module, a third text data display module and a second virtual article display module.
The third mapping display module is used for displaying the first texture mapping on the operation interface; the third text data display module is used for responding to a second feedback instruction acting on the operation interface and displaying second text data on the operation interface, wherein the second text data is text data obtained by modifying the first text data based on the second feedback instruction; the second virtual object display module is used for displaying a target virtual object on the operation interface, wherein the target virtual object is generated by rendering the target three-dimensional model based on a second texture map, and the second texture map is generated based on the second text data and texture information corresponding to the target three-dimensional model.
In the above embodiment of the present application, the method further includes: the display device comprises a third display module, a fourth display module and a fifth display module.
The third display module is used for displaying at least one recommendation type and at least one recommendation color on the operation interface; the fourth display module is used for responding to a first selection instruction acting on at least one recommendation type and a second selection instruction acting on at least one recommendation color, displaying a target recommendation type corresponding to the first selection instruction in the operation interface, and displaying a target recommendation color corresponding to the second selection instruction; the fifth display module is used for displaying a target virtual object on the operation interface, wherein the target virtual object is generated by rendering a three-dimensional model corresponding to the target recommendation type based on a third texture map, and the third texture map is generated based on the first text data, the target recommendation color and texture information corresponding to the target three-dimensional model.
Example 8
According to an embodiment of the present application, there is further provided a virtual clothes generating apparatus for implementing the virtual clothes generating method, and fig. 13 is a schematic diagram of a virtual clothes generating apparatus according to embodiment 3 of the present application, as shown in fig. 13, where the apparatus includes: a capture module 1302, a determination module 1304, a generation module 1306, and a rendering module 1308.
The capturing module is used for capturing a first text describing the type of the target virtual clothes and a second text describing the texture of the target virtual clothes, wherein the virtual clothes are used for representing clothes rendered in a virtual environment; the determining module is used for determining a target clothing model corresponding to the target virtual clothing from a plurality of preset clothing models based on the first text, wherein different preset clothing models are used for representing different types of virtual clothing; the generating module is used for generating a first texture map corresponding to the target clothing model based on the second text and texture information corresponding to the target clothing model; the rendering module is used for rendering the target clothing model based on the first texture map and generating the target virtual clothing.
It should be noted that, the capturing module 1302, the determining module 1304, the generating module 1306 and the rendering module 1308 correspond to steps S802 to S808 in embodiment 3, and the four modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to those disclosed in embodiment 1. It should be noted that the above modules or units may be hardware components or software components stored in a memory and processed by one or more processors, or the above modules may also be part of an apparatus and may be run in the AR/VR device provided in embodiment 1.
Example 9
According to an embodiment of the present application, there is further provided a virtual article generating apparatus for implementing the virtual article generating method described above, and fig. 14 is a schematic diagram of a virtual article generating apparatus according to embodiment 4 of the present application, as shown in fig. 14, including: a first display module 1402, a determination module 1404, a generation module 1406, a rendering module 1408, and a second display module 14010.
The first display module is used for displaying first text data on a display picture of the virtual reality VR device or the augmented reality AR device, wherein the first text data at least comprises a first text used for describing the type of a target virtual object and a second text used for describing the texture of the target virtual object, and the target virtual object is used for representing the object rendered in the virtual environment; the determining module is used for determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; the generating module is used for generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; the rendering module is used for rendering the target three-dimensional model based on the first texture map to generate a target virtual article; the second display module is used for driving the VR device or the AR device to display the target virtual object.
Here, the first display module 1402, the determining module 1404, the generating module 1406, the rendering module 1408, and the second display module 14010 correspond to steps S902 to S9010 in embodiment 4, and the five modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to those disclosed in embodiment 1. It should be noted that the above modules or units may be hardware components or software components stored in a memory and processed by one or more processors, or the above modules may also be part of an apparatus and may be run in the AR/VR device provided in embodiment 1.
Example 10
According to an embodiment of the present application, there is further provided a virtual article generating apparatus for implementing the virtual article generating method described above, and fig. 15 is a schematic diagram of a virtual article generating apparatus according to embodiment 5 of the present application, as shown in fig. 15, including: an acquisition module 1502, a determination module 1504, a generation module 1506, a rendering module 1508, and an output module 15010.
The method comprises the steps that an acquisition module is used for acquiring first text data by calling a first interface, wherein the first interface comprises first parameters, parameter values of the first parameters are the first text data, the first text data at least comprise first texts used for describing types of target virtual articles and second texts used for describing textures of the target virtual articles, and the target virtual articles are used for representing articles rendered in a virtual environment; the determining module is used for determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; the generating module is used for generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; the rendering module is used for rendering the target three-dimensional model based on the first texture map to generate a target virtual article; the output module is used for outputting the target virtual article by calling a second interface, wherein the second interface comprises a second parameter, and the parameter value of the second parameter is the target virtual article.
Here, the above is to be noted: the acquisition module 1502, the determination module 1504, the generation module 1506, the rendering module 1508, and the output module 15010 correspond to steps S1002 to S10010 in embodiment 5, and the five modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to those disclosed in embodiment 1 above. It should be noted that the above modules or units may be hardware components or software components stored in a memory and processed by one or more processors, or the above modules may also be part of an apparatus and may be run in the AR/VR device provided in embodiment 1.
Example 11
Embodiments of the present application may provide an AR/VR device that may be any one of a group of AR/VR devices. Alternatively, in this embodiment, the AR/VR device may be replaced by a terminal device such as a mobile terminal.
Alternatively, in this embodiment, the AR/VR device may be located in at least one network device among a plurality of network devices of the computer network.
In this embodiment, the above-mentioned AR/VR device may execute the program codes of the following steps in the virtual article generating method: displaying first text data on a presentation screen of a Virtual Reality (VR) device or an Augmented Reality (AR) device, wherein the first text data at least comprises a first text for describing the type of a target virtual article and a second text for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in a virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object; the VR device or AR device is driven to present the target virtual article.
Alternatively, fig. 16 is a block diagram of a computer terminal according to an embodiment of the present application. As shown in fig. 16, the computer terminal a may include: one or more (only one is shown) processors 1602, memory 1604, a memory controller, and a peripheral interface, where the peripheral interface is connected to a radio frequency module, an audio module, and a display.
The memory may be used to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for generating a virtual article in the embodiments of the present application, and the processor executes the software programs and modules stored in the memory, thereby executing various functional applications and data processing, that is, implementing the method for generating a virtual article described above. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory remotely located with respect to the processor, which may be connected to terminal a through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The processor may call the information and the application program stored in the memory through the transmission device to perform the following steps: acquiring first text data, wherein the first text data at least comprises a first text for describing the type of a target virtual article and a second text for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object.
Optionally, the above processor may further execute program code for: performing text recognition on the first text, and determining a target type; and acquiring a preset three-dimensional model corresponding to the type of the target virtual object from the plurality of preset three-dimensional models to obtain a target three-dimensional model.
Optionally, the above processor may further execute program code for: tiling the target three-dimensional model according to a preset tiling method to obtain texture information; extracting features of the first text data to obtain first text features; extracting priori knowledge from the first text features to generate first image features; and performing feature decoding on the first image features based on the texture information by using the diffusion model to generate a first texture map.
Optionally, the above processor may further execute program code for: acquiring an article image obtained by shooting an entity article in a real environment; generating original text data based on the object image, wherein the original text data at least comprises text for describing the type of the entity object and text for describing the texture of the entity object; outputting original text data; and under the condition that the modification instruction is received, modifying the original text data based on the modification instruction to obtain the first text data.
Optionally, the above processor may further execute program code for: extracting features of the object image to obtain second image features; extracting priori knowledge from the second image features to generate second text features; and performing feature decoding on the second text feature to generate original text data.
Optionally, the above processor may further execute program code for: outputting a first texture map; obtaining a feedback texture map, wherein the feedback texture map is a texture map obtained by modifying a partial region in the first texture map; rendering the target three-dimensional model based on the feedback texture map to generate a target virtual object.
Optionally, the above processor may further execute program code for: outputting a first texture map; acquiring second text data, wherein the second text data is text data obtained by modifying the first text data based on the first texture map; generating a second texture map corresponding to the target three-dimensional model based on the second text data and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the second texture map to generate a target virtual object.
Optionally, the above processor may further execute program code for: outputting at least one recommendation type and at least one recommendation color; determining a target recommendation type selected from the at least one recommendation type and a target recommendation color selected from the at least one recommendation color; generating a third texture map corresponding to the target three-dimensional model based on the first text data, the target recommended color and texture information corresponding to the target three-dimensional model; rendering the three-dimensional model corresponding to the target recommendation type based on the third texture map, and generating the target virtual object.
In the embodiment of the application, first text data is acquired, wherein the first text data at least comprises a first text for describing the type of a target virtual object and a second text for describing the texture of the target virtual object, and the target virtual object is used for representing the object rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; and rendering the target three-dimensional model based on the first texture map to generate a target virtual object. It is easy to notice that, in the application, the common user can quickly and automatically generate the virtual article only by inputting simple text description, the common user does not need to design the virtual article by himself, the target three-dimensional model is obtained by screening a plurality of preset three-dimensional models, the resolution of the target three-dimensional model is higher, the texture map is generated based on texts, the resolution of the texture map is higher and is closer to the material of real clothing, the purpose of improving the generation effect of generating the virtual article is achieved, the technical effect of improving the generation effect of generating the virtual article is achieved, and the technical problem that the generation effect of generating the virtual article in the related technology is poor is solved.
It will be appreciated by those skilled in the art that the structure shown in the figure is only illustrative, and the computer terminal may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a mobile internet device (MobileInternetDevices, MID), a PAD, etc. Fig. 16 does not limit the structure of the electronic device. For example, the computer terminal a may also include more or fewer components (such as a network interface, a display device, etc.) than shown in fig. 16, or have a different configuration than shown in fig. 16.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program for instructing a terminal device to execute in association with hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: flash disk, read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic or optical disk, and the like.
Example 12
Embodiments of the present application also provide a computer-readable storage medium. Alternatively, in this embodiment, the computer-readable storage medium may be used to store program code executed by the virtual article generating method provided in embodiment 1.
Alternatively, in this embodiment, the above-mentioned computer readable storage medium may be located in any one of the AR/VR device terminals in the AR/VR device network or in any one of the mobile terminals in the mobile terminal group.
Optionally, in the present embodiment, the computer readable storage medium is configured to store program code for performing the steps of: acquiring first text data, wherein the first text data at least comprises a first text for describing the type of a target virtual article and a second text for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in the virtual environment; determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects; generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the first texture map to generate a target virtual object.
Optionally, in the present embodiment, the computer readable storage medium is further configured to store program code for performing the steps of: performing text recognition on the first text, and determining a target type; and acquiring a preset three-dimensional model corresponding to the type of the target virtual object from the plurality of preset three-dimensional models to obtain a target three-dimensional model.
Optionally, in the present embodiment, the computer readable storage medium is further configured to store program code for performing the steps of: tiling the target three-dimensional model according to a preset tiling method to obtain texture information; extracting features of the first text data to obtain first text features; extracting priori knowledge from the first text features to generate first image features; and performing feature decoding on the first image features based on the texture information by using the diffusion model to generate a first texture map.
Optionally, in the present embodiment, the computer readable storage medium is further configured to store program code for performing the steps of: acquiring an article image obtained by shooting an entity article in a real environment; generating original text data based on the object image, wherein the original text data at least comprises text for describing the type of the entity object and text for describing the texture of the entity object; outputting original text data; and under the condition that the modification instruction is received, modifying the original text data based on the modification instruction to obtain the first text data.
Optionally, in the present embodiment, the computer readable storage medium is further configured to store program code for performing the steps of: extracting features of the object image to obtain second image features; extracting priori knowledge from the second image features to generate second text features; and performing feature decoding on the second text feature to generate original text data.
Optionally, in the present embodiment, the computer readable storage medium is further configured to store program code for performing the steps of: outputting a first texture map; obtaining a feedback texture map, wherein the feedback texture map is a texture map obtained by modifying a partial region in the first texture map; rendering the target three-dimensional model based on the feedback texture map to generate a target virtual object.
Optionally, in the present embodiment, the computer readable storage medium is further configured to store program code for performing the steps of: outputting a first texture map; acquiring second text data, wherein the second text data is text data obtained by modifying the first text data based on the first texture map; generating a second texture map corresponding to the target three-dimensional model based on the second text data and texture information corresponding to the target three-dimensional model; rendering the target three-dimensional model based on the second texture map to generate a target virtual object.
Optionally, in the present embodiment, the computer readable storage medium is further configured to store program code for performing the steps of: outputting at least one recommendation type and at least one recommendation color; determining a target recommendation type selected from the at least one recommendation type and a target recommendation color selected from the at least one recommendation color; generating a third texture map corresponding to the target three-dimensional model based on the first text data, the target recommended color and texture information corresponding to the target three-dimensional model; rendering the three-dimensional model corresponding to the target recommendation type based on the third texture map, and generating the target virtual object.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, such as the division of the units, is merely a logical function division, and may be implemented in another manner, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-only memory (ROM), a random access memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application, which are intended to be comprehended within the scope of the present application.
Claims (14)
1. A method of generating a virtual article, comprising:
acquiring first text data, wherein the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing an article rendered in a virtual environment;
determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects;
generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model;
rendering the target three-dimensional model based on the first texture map, and generating the target virtual object.
2. The method of claim 1, wherein determining, based on the first text, a target three-dimensional model corresponding to the type of the target virtual article from a plurality of preset three-dimensional models, comprises:
performing text recognition on the first text, and determining a target type;
and acquiring a preset three-dimensional model corresponding to the type of the target virtual object from the plurality of preset three-dimensional models to obtain the target three-dimensional model.
3. The method of claim 1, wherein generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model comprises:
tiling the target three-dimensional model according to a preset tiling method to obtain the texture information;
extracting the characteristics of the first text data to obtain first text characteristics;
extracting priori knowledge from the first text features to generate first image features;
and performing feature decoding on the first image features based on the texture information by using a diffusion model to generate the first texture map.
4. The method of claim 1, wherein obtaining the first text data comprises:
Acquiring an article image obtained by shooting an entity article in a real environment;
generating original text data based on the object image, wherein the original text data at least comprises text for describing the type of the entity object and text for describing the texture of the entity object;
outputting the original text data;
and under the condition that a modification instruction is received, modifying the original text data based on the modification instruction to obtain the first text data.
5. The method of claim 4, wherein generating raw text data based on the item image comprises:
extracting features of the object image to obtain a second image feature;
extracting priori knowledge from the second image features to generate second text features;
and performing feature decoding on the second text feature to generate the original text data.
6. The method of claim 1, wherein after generating the first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model, the method further comprises:
Outputting the first texture map;
obtaining a feedback texture map, wherein the feedback texture map is a texture map obtained by modifying a partial region in the first texture map;
rendering the target three-dimensional model based on the feedback texture map to generate the target virtual article.
7. The method of claim 1, wherein after generating a first texture map corresponding to the target three-dimensional model based on the first text data, the method further comprises:
outputting the first texture map;
acquiring second text data, wherein the second text data is text data obtained by modifying the first text data based on the first texture map;
generating a second texture map corresponding to the target three-dimensional model based on the second text data and texture information corresponding to the target three-dimensional model;
rendering the target three-dimensional model based on the second texture map, and generating the target virtual object.
8. The method according to claim 1, wherein the method further comprises:
outputting at least one recommendation type and at least one recommendation color;
Determining a target recommendation type selected from the at least one recommendation type and a target recommendation color selected from the at least one recommendation color;
generating a third texture map corresponding to the target three-dimensional model based on the first text data, the target recommended color and texture information corresponding to the target three-dimensional model;
and rendering the three-dimensional model corresponding to the target recommendation type based on the third texture map, and generating the target virtual object.
9. A method of generating a virtual article, comprising:
responding to an input instruction acted on an operation interface, and displaying first text data on the operation interface, wherein the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing an article rendered in a virtual environment;
and responding to a rendering instruction acting on the operation interface, and displaying the target virtual object on the operation interface, wherein the target virtual object is generated by rendering a target three-dimensional model based on a first texture map, the first texture map is generated based on the second text and texture information corresponding to the target three-dimensional model, the target three-dimensional model is a model corresponding to the type of the target virtual object determined from a plurality of preset three-dimensional models based on the first text, and different preset three-dimensional models are used for representing different types of virtual objects.
10. A method of generating virtual apparel, comprising:
capturing a first text describing the type of the target virtual clothes and a second text describing the texture of the target virtual clothes, wherein the virtual clothes are used for representing clothes rendered in a virtual environment;
determining a target clothing model corresponding to the target virtual clothing from a plurality of preset clothing models based on the first text, wherein different preset clothing models are used for representing different types of virtual clothing;
generating a first texture map corresponding to the target clothing model based on the second text and texture information corresponding to the target clothing model;
rendering the target clothing model based on the first texture map, and generating the target virtual clothing.
11. A method of generating a virtual article, comprising:
displaying first text data on a presentation screen of a Virtual Reality (VR) device or an Augmented Reality (AR) device, wherein the first text data at least comprises a first text for describing the type of a target virtual article and a second text for describing the texture of the target virtual article, and the target virtual article is used for representing an article rendered in a virtual environment;
Determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects;
generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model;
rendering the target three-dimensional model based on the first texture map to generate the target virtual article;
and driving the VR equipment or the AR equipment to display the target virtual object.
12. A method of generating a virtual article, comprising:
acquiring first text data by calling a first interface, wherein the first interface comprises a first parameter, the parameter value of the first parameter is the first text data, the first text data at least comprises a first text used for describing the type of a target virtual article and a second text used for describing the texture of the target virtual article, and the target virtual article is used for representing the article rendered in a virtual environment;
determining a target three-dimensional model corresponding to the type of the target virtual object from a plurality of preset three-dimensional models based on the first text, wherein different preset three-dimensional models are used for representing different types of virtual objects;
Generating a first texture map corresponding to the target three-dimensional model based on the second text and texture information corresponding to the target three-dimensional model;
rendering the target three-dimensional model based on the first texture map to generate the target virtual article;
and outputting the target virtual article by calling a second interface, wherein the second interface comprises a second parameter, and the parameter value of the second parameter is the target virtual article.
13. An electronic device, comprising:
a memory storing an executable program;
a processor for executing the program, wherein the program when run performs the method of any of claims 1 to 12.
14. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored executable program, wherein the executable program when run controls a device in which the computer readable storage medium is located to perform the method of any one of claims 1 to 12.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310530954.2A CN116630500A (en) | 2023-05-11 | 2023-05-11 | Virtual article generation method, virtual clothing generation method and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310530954.2A CN116630500A (en) | 2023-05-11 | 2023-05-11 | Virtual article generation method, virtual clothing generation method and electronic device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116630500A true CN116630500A (en) | 2023-08-22 |
Family
ID=87591223
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310530954.2A Pending CN116630500A (en) | 2023-05-11 | 2023-05-11 | Virtual article generation method, virtual clothing generation method and electronic device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116630500A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117218266A (en) * | 2023-10-26 | 2023-12-12 | 神力视界(深圳)文化科技有限公司 | 3D white-mode texture map generation method, device, equipment and medium |
CN117557709A (en) * | 2024-01-10 | 2024-02-13 | 支付宝(杭州)信息技术有限公司 | Method and device for generating digital human clothing |
-
2023
- 2023-05-11 CN CN202310530954.2A patent/CN116630500A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117218266A (en) * | 2023-10-26 | 2023-12-12 | 神力视界(深圳)文化科技有限公司 | 3D white-mode texture map generation method, device, equipment and medium |
CN117557709A (en) * | 2024-01-10 | 2024-02-13 | 支付宝(杭州)信息技术有限公司 | Method and device for generating digital human clothing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116630500A (en) | Virtual article generation method, virtual clothing generation method and electronic device | |
CN111641844B (en) | Live broadcast interaction method and device, live broadcast system and electronic equipment | |
CN108711180B (en) | Method and device for generating makeup and/or face-changing special effect program file package and method and device for generating makeup and/or face-changing special effect | |
CN113099298B (en) | Method and device for changing virtual image and terminal equipment | |
CN112199016B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
CN108668050B (en) | Video shooting method and device based on virtual reality | |
JP2023539620A (en) | Facial image processing method, display method, device and computer program | |
CN111767817B (en) | Dress collocation method and device, electronic equipment and storage medium | |
CN111862116A (en) | Animation portrait generation method and device, storage medium and computer equipment | |
CN111429543B (en) | Material generation method and device, electronic equipment and medium | |
CN114241132B (en) | Scene content display control method and device, computer equipment and storage medium | |
CN114285944B (en) | Video color ring generation method and device and electronic equipment | |
CN116485973A (en) | Material generation method of virtual object, electronic equipment and storage medium | |
CN117011417A (en) | Image processing method and device and computer equipment | |
CN114004772A (en) | Image processing method, image synthesis model determining method, system and equipment | |
KR20200085029A (en) | Avatar virtual pitting system | |
CN113069763A (en) | Game role reloading method and device and electronic equipment | |
CN116112761B (en) | Method and device for generating virtual image video, electronic equipment and storage medium | |
CN116630508A (en) | 3D model processing method and device and electronic equipment | |
CN115953514A (en) | Avatar generation method and storage medium | |
CN114779948B (en) | Method, device and equipment for controlling instant interaction of animation characters based on facial recognition | |
CN116485983A (en) | Texture generation method of virtual object, electronic device and storage medium | |
KR102617789B1 (en) | Picture processing methods and devices, storage media and electronic devices | |
CN116129006A (en) | Data processing method, device, equipment and readable storage medium | |
KR20120097589A (en) | Computing device, method and system for embodying augmented reality |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |