WO2022083213A1 - 图像生成方法、装置、设备和计算机可读介质 - Google Patents

图像生成方法、装置、设备和计算机可读介质 Download PDF

Info

Publication number
WO2022083213A1
WO2022083213A1 PCT/CN2021/109552 CN2021109552W WO2022083213A1 WO 2022083213 A1 WO2022083213 A1 WO 2022083213A1 CN 2021109552 W CN2021109552 W CN 2021109552W WO 2022083213 A1 WO2022083213 A1 WO 2022083213A1
Authority
WO
WIPO (PCT)
Prior art keywords
hand
image
target
dimensional model
ornament
Prior art date
Application number
PCT/CN2021/109552
Other languages
English (en)
French (fr)
Inventor
卢艺帆
Original Assignee
北京字跳网络技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京字跳网络技术有限公司 filed Critical 北京字跳网络技术有限公司
Publication of WO2022083213A1 publication Critical patent/WO2022083213A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0641—Shopping interfaces
    • G06Q30/0643—Graphical representation of items or shoppers
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/107—Static hand or arm

Definitions

  • Embodiments of the present disclosure relate to the field of computer technology, and in particular, to an image generation method, apparatus, device, and computer-readable medium.
  • Some embodiments of the present disclosure propose methods, apparatuses, devices, and computer-readable media for image generation to solve the technical problems mentioned in the background section above.
  • some embodiments of the present disclosure provide an image generation method, the method comprising: adjusting a three-dimensional model of a hand including a hand ornament to obtain a three-dimensional model combination adapted to a target hand image; Rendering the three-dimensional model of the hand ornament in the above-mentioned three-dimensional model combination adapted to the target hand image to obtain a hand ornament image; combining the above-mentioned hand ornament image and the above-mentioned target hand image to obtain a hand ornament image including the hand ornament image. hand image of an ornament.
  • some embodiments of the present disclosure provide an apparatus for image generation, the apparatus comprising: a model adjustment unit configured to adjust a three-dimensional model of a hand including a hand ornament to obtain an image suitable for a target hand.
  • the matching three-dimensional model combination the model rendering unit is configured to render the three-dimensional model of the hand ornament in the above-mentioned three-dimensional model combination adapted to the target hand image to obtain the hand ornament image;
  • the image combining unit is configured The above-mentioned hand ornament image and the above-mentioned target hand image are combined to obtain a hand image including the hand ornament.
  • some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device on which one or more programs are stored, when one or more programs are stored by one or more The processor executes, causing the one or more processors to implement a method as described in any one of the implementations of the first aspect, or to implement a method as described in any of the implementations of the third aspect.
  • some embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementation manners of the first aspect, or implements A method as described in any implementation of the third aspect.
  • One of the above-mentioned embodiments of the present disclosure has the following beneficial effects: by adjusting the three-dimensional model of the hand including the hand decoration, the decoration picture can be accurately fitted on the hand picture.
  • the image of the hand ornament fitted with the hand image can be obtained.
  • the hand image with the ornament can be obtained. Thereby, the wearing effect can be presented. On this basis, users can observe whether the decorations fit their hands.
  • FIG. 1 is a schematic diagram of an application scenario of an image generation method according to some embodiments of the present disclosure
  • FIG. 3 is a flowchart of other embodiments of image generation methods according to the present disclosure.
  • FIG. 4 is a schematic diagram of another application scenario of the image generation method according to some embodiments of the present disclosure.
  • FIG. 5 is a schematic structural diagram of some embodiments of an image generating apparatus according to the present disclosure.
  • FIG. 6 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure.
  • FIG. 1 is a schematic diagram 100 of an application scenario of an image generation method according to some embodiments of the present disclosure.
  • the computing device 101 may adjust the three-dimensional hand model 102 containing the hand ornament, for example, may rotate and translate the three-dimensional hand model 102 containing the hand ornament.
  • a three-dimensional model combination 103 adapted to the target hand image is obtained.
  • the hand ornament image 104 can be obtained by rendering the three-dimensional model of the hand ornament in the above-mentioned three-dimensional model combination 103 adapted to the target hand image. Then, the above-mentioned hand ornament image 104 and the above-mentioned target hand image are combined to obtain a hand image 105 including the hand ornament.
  • the image generation method may be executed by the computing device 101, or may also be executed by a server, and the execution subject of the above method may also include a device formed by integrating the above-mentioned computing device 101 and the above-mentioned server through a network, Or it can also be executed by various software programs.
  • the computing device 101 may be various electronic devices with information processing capabilities, including but not limited to smart phones, tablet computers, e-book readers, laptop computers, desktop computers, and the like.
  • the execution body may also be embodied as a server, software, or the like. When the execution body is software, it can be installed in the electronic devices listed above. It can be implemented, for example, as multiple software or software modules for providing distributed services, or as a single software or software module. There is no specific limitation here.
  • the image generation method includes the following steps:
  • Step 201 adjust the three-dimensional model of the hand including the hand ornament to obtain a three-dimensional model combination that is adapted to the target hand image.
  • the three-dimensional hand model containing the hand ornament includes a three-dimensional model of the hand ornament and a three-dimensional model of the hand.
  • the three-dimensional model of the hand ornament can be a three-dimensional model of various ornaments. For example, it can be a three-dimensional model of a ring, or a three-dimensional model of a finger cuff.
  • the three-dimensional model of the hand may be a three-dimensional model of the hand.
  • the three-dimensional hand model containing the hand ornament may be a combination of a three-dimensional model of the hand ornament and a three-dimensional model of the hand.
  • the position and shape of the three-dimensional model of the hand containing the hand ornament can be adjusted.
  • a 3D model combination suitable for the target hand image can be obtained.
  • the adjustment of the 3D model of the hand including the hand decoration may be to rotate the 3D model of the hand including the hand decoration, or it may be to adjust the 3D model of the hand including the hand decoration.
  • the 3D model of the product's hand is translated.
  • Step 202 Render the three-dimensional model of the hand ornament in the above-mentioned three-dimensional model combination adapted to the target hand image to obtain an image of the hand ornament.
  • the target hand image may be any image showing a hand.
  • the determination of the target hand image can be obtained by designation or by filtering through certain conditions.
  • the image of the user's hand currently captured by the camera may be determined as the target hand image.
  • the rendering of the three-dimensional model of the hand ornament in the combination of the three-dimensional models adapted to the target hand image may be by projecting the three-dimensional model of the hand ornament along the target direction to generate a two-dimensional hand ornament. decorative image.
  • the three-dimensional model of the hand ornament is projected, and along the target projection direction, the part of the three-dimensional model of the hand that is not blocked by the three-dimensional model of the finger is projected to generate the image of the hand ornament.
  • Step 203 Combine the above-mentioned hand ornament image and the above-mentioned target hand image to obtain a hand image including the hand ornament.
  • the above-mentioned hand ornament image is overlaid on the finger matched with the target hand image to obtain a hand image including the hand ornament.
  • One of the above-mentioned embodiments of the present disclosure has the following beneficial effect: by adjusting the three-dimensional model of the hand including the hand ornament, the ornament picture can be accurately fitted on the hand picture. Afterwards, rendering is performed on the three-dimensional model of the hand ornament in the combination of the above three-dimensional models adapted to the target hand image, so as to obtain an image of the hand ornament fitted with the hand image. Finally, the above-mentioned hand ornament image and the above-mentioned target hand image are combined to obtain a hand image wearing the ornament, so as to present the wearing effect of the ornament. On this basis, users can see if the decorations fit their hands.
  • the image generation method includes the following steps:
  • Step 301 based on the target hand image, generate a three-dimensional model of the target hand.
  • the 3D model of the target hand may be a 3D model with hand features in the target hand image.
  • the target hand image can be passed into the neural network to generate data with hand features, and then the data with hand features can be passed to the rendering engine, and the three-dimensional model of the target hand can be obtained through rendering by the rendering engine. It is also possible to obtain data with hand features by measuring the hand, and input the data with hand features into the rendering engine for rendering to obtain a three-dimensional model of the target hand.
  • three-dimensional hand key points are generated based on the above-mentioned target hand image.
  • the target hand image can be passed into the pre-trained dense convolutional network (DenseNet), and the 3D coordinates output by the dense convolutional network (DenseNet) can be used as the 3D hand key points.
  • DenseNet dense convolutional network
  • the above-mentioned 3D hand key points are rendered by a 3D rendering engine, and the 3D hand key points are smoothly connected and the 3D model is filled to obtain a 3D model of the target hand.
  • the target hand image may be input into a pre-trained 3D point cloud network (PointNet), and the 3D point cloud network (PointNet) outputs a 3D point set.
  • PointNet 3D point cloud network
  • the 3D rendering engine uses the keypoint set in the three-dimensional point set to determine the hand joint point position coefficient and hand shape coefficient that are suitable for the target hand image.
  • the above-mentioned hand joint point position coefficient and hand shape coefficient are used to adjust the initial 3D model of the hand obtained in advance by the 3D rendering engine.
  • the 3D rendering engine will adjust the output model as the 3D model of the target hand.
  • the above hand joint point position coefficients can control the action of the target hand 3D model
  • the hand shape coefficients can control the length of each joint of the target hand 3D model and the shape and size of each part of the hand.
  • Step 302 Combine the above-mentioned target three-dimensional model of the hand and the three-dimensional model of the hand ornament to obtain the above-mentioned three-dimensional model of the hand including the hand ornament.
  • the finger three-dimensional model of the target hand three-dimensional model may be combined with a pre-obtained three-dimensional model of hand ornaments.
  • FIG. 4 is a schematic diagram 400 of an application scenario of steps 301 and 302 of an image generation method according to some embodiments of the present disclosure.
  • a 3D model of the target hand 405 is generated, wherein the computing device 401 can input the target hand image 402 into the neural network 403 that can generate 3D hand key points, thereby obtaining 3D hand keypoints 404 .
  • the above three-dimensional hand key points 404 are connected and rendered to generate a target hand three-dimensional model 405 .
  • the target hand three-dimensional model 405 and the hand ornament three-dimensional model 406 are combined to obtain the above-mentioned hand three-dimensional model 407 including the hand ornament.
  • Step 303 adjusting the three-dimensional model of the hand including the hand ornament to obtain a three-dimensional model combination adapted to the target hand image.
  • Step 304 Render the three-dimensional model of the hand ornament in the above-mentioned three-dimensional model combination adapted to the target hand image to obtain an image of the hand ornament.
  • Step 305 Combine the above-mentioned hand ornament image and the above-mentioned target hand image to obtain a hand image including the hand ornament.
  • steps 303 , 304 and 305 for the specific implementation of steps 303 , 304 and 305 and the technical effects brought about by them, reference may be made to steps 201 , 202 and 203 in the embodiment corresponding to FIG. 2 , and details are not repeated here.
  • the image generation methods disclosed in some embodiments of the present disclosure compared with those of the embodiments corresponding to FIG. 2 , add a step of generating a three-dimensional model of a hand including a hand ornament. Among them, based on the target hand image, a three-dimensional model that is accurately adapted to the hand can be generated. Therefore, the presented wearing effect is more accurate.
  • the present disclosure provides some embodiments of an image generating apparatus, and these apparatus embodiments correspond to those method embodiments shown in FIG. 2 . Can be used in various electronic devices.
  • the image generation apparatus 500 of some embodiments includes: a model adjustment unit 501 configured to adjust a three-dimensional model of a hand including a hand ornament to obtain a three-dimensional model combination suitable for the target hand image .
  • the model rendering unit 502 is configured to render the three-dimensional model of the hand ornament in the above-mentioned three-dimensional model combination adapted to the target hand image to obtain the image of the hand ornament.
  • the image combining unit 503 is configured to combine the above-mentioned hand ornament image and the above-mentioned target hand image to obtain a hand image including the hand ornament.
  • the above-mentioned apparatus 500 further includes: a model generating unit, configured to generate a three-dimensional model of the target hand based on the above-mentioned target hand image; a model combining unit, configured to generate the above-mentioned target hand The three-dimensional model and the three-dimensional model of the hand ornament are combined to obtain the above-mentioned three-dimensional model of the hand including the hand ornament.
  • the model generating unit is further configured to: generate three-dimensional hand key points based on the target hand image; and generate the above-mentioned three-dimensional model of the target hand based on the above-mentioned three-dimensional hand key points.
  • the model generating unit may be further configured to: determine the target coefficient of the above-mentioned target hand image; based on the above-mentioned target coefficient, adjust the pre-acquired initial three-dimensional model of the hand to obtain the above-mentioned target 3D model of the hand.
  • the above-mentioned target coefficient includes: a hand joint point position coefficient and a hand shape coefficient represented by the above-mentioned target hand image.
  • the model adjustment unit 501 is further configured to: rotate or translate the above-mentioned three-dimensional model of the hand including the hand ornament.
  • the units recorded in the apparatus 500 correspond to the respective steps in the method described with reference to FIG. 2 . Therefore, the operations, features and beneficial effects described above with respect to the method are also applicable to the apparatus 500 and the units included therein, and details are not described herein again.
  • an electronic device 600 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 601 that may be loaded into random access according to a program stored in a read only memory (ROM) 602 or from a storage device 608 Various appropriate actions and processes are executed by the programs in the memory (RAM) 603 . In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored.
  • the processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to bus 604 .
  • I/O interface 605 input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 607 of a computer, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609.
  • Communication means 609 may allow electronic device 600 to communicate wirelessly or by wire with other devices to exchange data. While FIG. 6 shows electronic device 600 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in FIG. 6 may represent one device, or may represent multiple devices as required.
  • the processes described above with reference to the flowcharts may be implemented as computer software programs.
  • some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via the communication device 609, or from the storage device 608, or from the ROM 602.
  • the processing device 601 When the computer program is executed by the processing device 601, the above-mentioned functions defined in the methods of some embodiments of the present disclosure are performed.
  • the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the client and server can use any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol) to communicate, and can communicate with digital data in any form or medium Communication (eg, a communication network) interconnects.
  • HTTP HyperText Transfer Protocol
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device is made to: adjust the three-dimensional model of the hand including the hand decoration, and obtain the same value as the target hand.
  • three-dimensional model combination adapted to the hand image rendering the three-dimensional model of the hand ornament in the above-mentioned three-dimensional model combination suitable for the target hand image to obtain the hand ornament image;
  • the hand images are combined to obtain a hand image including hand decorations.
  • Computer program code for carrying out operations of some embodiments of the present disclosure may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, or a combination thereof , as well as conventional procedural programming languages - such as "C" or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider to via Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the units described in some embodiments of the present disclosure may be implemented by means of software, and may also be implemented by means of hardware.
  • the described unit can also be provided in the processor, for example, it can be described as: a processor includes a configuration model adjustment unit, a model rendering unit and an image combination unit.
  • a processor includes a configuration model adjustment unit, a model rendering unit and an image combination unit.
  • the names of these units do not constitute a limitation of the unit itself under certain circumstances, for example, the model adjustment unit can also be described as "a unit for adjusting the three-dimensional model of the hand containing hand ornaments".
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logical Devices (CPLDs) and more.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLDs Complex Programmable Logical Devices
  • an image generation method comprising: adjusting a three-dimensional model of a hand including hand decorations to obtain a three-dimensional model combination suitable for a target hand image; Rendering the three-dimensional model of the hand ornament in the three-dimensional model combination adapted to the target hand image to obtain a hand ornament image; combining the above-mentioned hand ornament image and the above-mentioned target hand image to obtain a hand ornament including the hand ornament product's hand image.
  • the above method before adjusting the three-dimensional model of the hand including the hand ornament to obtain a combination of the three-dimensional model adapted to the target hand image, the above method further includes: based on the above-mentioned target hand image to generate a three-dimensional model of the target hand; combining the above-mentioned three-dimensional model of the target hand and the three-dimensional model of the hand ornament to obtain the above-mentioned three-dimensional model of the hand including the hand ornament.
  • generating the 3D model of the target hand based on the target hand image includes: generating 3D hand key points based on the target hand image; generating 3D hand key points based on the 3D hand key points The above-mentioned 3D model of the target hand.
  • generating a three-dimensional model of the target hand based on the target hand image includes: determining a target coefficient of the target hand image; adjusting a pre-acquired initial hand image based on the target coefficient A three-dimensional model is used to obtain the above-mentioned three-dimensional model of the target hand.
  • the above-mentioned target coefficient includes: a hand joint point position coefficient and a hand shape coefficient represented by the above-mentioned target hand image.
  • the above-mentioned adjustment of the three-dimensional model of the hand including the hand ornament to obtain a three-dimensional model combination suitable for the target hand image includes: Rotate or translate the part of the 3D model.
  • the image generation apparatus includes: a model adjustment unit configured to adjust a three-dimensional model of a hand including a hand ornament to obtain a three-dimensional model combination suitable for a target hand image.
  • the model rendering unit is configured to render the three-dimensional model of the hand ornament in the above-mentioned three-dimensional model combination adapted to the target hand image, so as to obtain the image of the hand ornament.
  • the image combining unit is configured to combine the above-mentioned hand ornament image and the above-mentioned target hand image to obtain a hand image including the hand ornament.
  • the above-mentioned apparatus further includes: a model generating unit configured to generate a three-dimensional model of the target hand based on the above-mentioned target hand image; a model combining unit configured to generate a three-dimensional model of the above-mentioned target hand The model and the three-dimensional model of the hand ornament are combined to obtain the above-mentioned three-dimensional model of the hand including the hand ornament.
  • the model generation unit is further configured to: generate three-dimensional hand key points based on the target hand image; and generate the above-mentioned target hand three-dimensional model based on the above-mentioned three-dimensional hand key points.
  • the model generating unit may be further configured to: determine the target coefficient of the target hand image; and adjust the initial three-dimensional model of the hand obtained in advance based on the target coefficient to obtain the target 3D model of the hand.
  • the above-mentioned target coefficient includes: a hand joint point position coefficient and a hand shape coefficient represented by the above-mentioned target hand image.
  • the model adjustment unit is further configured to: rotate or translate the above-mentioned three-dimensional model of the hand including the hand ornament.
  • an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, when the one or more programs are stored by one or more The processors execute such that one or more processors implement a method as in any of the above.
  • a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the foregoing embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Software Systems (AREA)
  • Finance (AREA)
  • Computer Graphics (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Geometry (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Processing Or Creating Images (AREA)

Abstract

本公开的实施例公开了图像生成方法、装置、电子设备和计算机可读介质。该方法的一具体实施方式包括：对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合；对上述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，得到手部装饰品图像；将上述手部装饰品图像和上述目标手部图像进行组合，得到包括手部装饰品的手部图像。该实施方式实现了对目标手部图像添加装饰品图像，能够呈现图片上的装饰品和手部的适配情况。

Description

图像生成方法、装置、设备和计算机可读介质
相关申请的交叉引用
本申请基于申请号为202011134814.6、申请日为2020年10月21日，名称为“图像生成方法、装置、设备和计算机可读介质”的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开的实施例涉及计算机技术领域，具体涉及图像生成方法、装置、设备和计算机可读介质。
背景技术
随着互联网技术的发展和以手机为例的电子设备的普及，与服饰和装饰品相关的信息可以通过各种电子设备进行呈现。人们通过各种电子设备可以看到各类装饰品的相关信息。但是，为了满足人们自身的穿戴需求，需要将装饰品的图像和手的图像进行组合，以呈现手部穿戴装饰品后的效果。
发明内容
本公开的内容部分用于以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。本公开的内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
本公开的一些实施例提出了图像生成的方法、装置、设备和计算机可读介质，来解决以上背景技术部分提到的技术问题。
第一方面，本公开的一些实施例提供了一种图像生成的方法，该方法包括：对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合；对上述与目标手部图像适配的三维模型组合中的手 部装饰品三维模型进行渲染，得到手部装饰品图像；将上述手部装饰品图像和上述目标手部图像进行组合，得到包括手部装饰品的手部图像。
第二方面，本公开的一些实施例提供了一种图像生成的装置，装置包括：模型调整单元，被配置成对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合；模型渲染单元，被配置成对上述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，得到手部装饰品图像；图像组合单元，被配置成将上述手部装饰品图像和上述目标手部图像进行组合，得到包括手部装饰品的手部图像。
第三方面，本公开的一些实施例提供了一种电子设备，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如第一方面中任一实现方式描述的方法，或实现第三方面中任一实现方式描述的方法。
第四方面，本公开的一些实施例提供了一种计算机可读介质，其上存储有计算机程序，其中，程序被处理器执行时实现如第一方面中任一实现方式描述的方法，或实现如第三方面中任一实现方式描述的方法。
本公开的上述各个实施例中的一个实施例具有如下有益效果：对包含手部装饰品的手部三维模型进行调整，可以使装饰品图片在手部图片上准确贴合。对与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，可以得到与手部图像进行贴合的手部装饰品图像。将手部装饰品图像和上述目标手部图像进行组合，可以得到带有装饰品的手部图像。从而可以呈现出穿戴效果。在此基础上，用户可以观察装饰品是否适合自己的手部。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1是根据本公开的一些实施例的图像生成方法的一个应用场景的示意图；
图2是根据本公开的图像生成方法的一些实施例的流程图；
图3是根据本公开的图像生成方法的另一些实施例的流程图；
图4是根据本公开的一些实施例的图像生成方法的另一个应用场景的示意图；
图5是根据本公开的图像生成装置的一些实施例的结构示意图；
图6是适于用来实现本公开的一些实施例的电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。相反，提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
下面将参考附图并结合实施例来详细说明本公开。
图1是根据本公开一些实施例的图像生成方法的一个应用场景的示意图100。
如图1所示，计算设备101可以对包含手部装饰品的手部三维模型102进行调整，例如，可以对包含手部装饰品的手部三维模型102进行旋转和平移。得到与目标手部图像适配的三维模型组合103。对上述与目标手部图像适配的三维模型组合103中的手部装饰品三维模型进行渲染，可以得 到手部装饰品图像104。之后，将上述手部装饰品图像104和上述目标手部图像进行组合，得到包括手部装饰品的手部图像105。
可以理解的是，图像生成方法可以是由计算设备101来执行，或者也可以是由服务器来执行，上述方法的执行主体还可以包括上述计算设备101与上述服务器通过网络相集成所构成的设备，或者还可以是各种软件程序来执行。其中，计算设备101可以是具有信息处理能力的各种电子设备，包括但不限于智能手机、平板电脑、电子书阅读器、膝上型便携计算机和台式计算机等等。此外，执行主体也可以体现为服务器、软件等。当执行主体为软件时，可以安装在上述所列举的电子设备中。其可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
应该理解，图1中的计算设备数目仅仅是示意性的。根据实现需要，可以具有任意数目的计算设备。
继续参考图2，示出了根据本公开的图像生成方法的一些实施例的流程200。该图像生成方法，包括以下步骤：
步骤201，对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合。
在一些实施例中，包含手部装饰品的手部三维模型中包括手部装饰品三维模型和手部三维模型。手部装饰品三维模型可以是各种装饰品的三维模型。例如，可以是戒指三维模型，也可以是指套的三维模型。
在一些实施例中，手部三维模型可以是手部的三维模型。
在一些实施例中，包含手部装饰品的手部三维模型可以是手部装饰品三维模型和手部三维模型的组合。
在一些实施例中，可以对包含手部装饰品的手部三维模型的位置和形状进行调整。在调整过程中，当上述包含手部装饰品的手部三维模型的投影图像与上述目标手部图像中所显示的手部重合时，可以得到与目标手部图像适配的三维模型组合。
在一些实施例的一些可选实现方式中，对包含手部装饰品的手部三维模型进行调整，可以是对包含手部装饰品的手部三维模型进行旋转，也可 以是对包含手部装饰品的手部三维模型进行平移。
步骤202，对上述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，得到手部装饰品图像。
在一些实施例中，目标手部图像可以是***示有手部的图像。目标手部图像的确定可以通过指定，也可以通过一定的条件筛选得到。作为示例，可以将当前通过摄像头拍摄的用户手部的图像确定为目标手部图像。
在一些实施例中，对上述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，可以是将手部装饰品三维模型沿目标方向进行投影，生成二维的手部装饰品图像。作为示例，对手部装饰品三维模型进行投影，沿目标投影方向，未被手部三维模型中的手指三维模型遮挡的部分的投影，生成手部装饰品图像。
步骤203，将上述手部装饰品图像和上述目标手部图像进行组合，得到包括手部装饰品的手部图像。
在一些实施例中，将上述手部装饰品图像覆盖到目标手部图像相适配的手指上，得到包括手部装饰品的手部图像。
本公开的上述各个实施例中的一个实施例具有如下有益效果：通过将包含手部装饰品的手部三维模型调整，使装饰品图片在手部图片上准确贴合。之后，对上述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，从而得到与手部图像进行贴合的手部装饰品图像。最后，将上述手部装饰品图像和上述目标手部图像进行组合，得到戴装饰品的手部图像，从而呈现出装饰品的穿戴效果。在此基础上，用户可以查看装饰品是否适合自己的手部。
继续参考图3，示出了根据本公开的图像生成方法的另一些实施例的流程300。该图像生成方法，包括以下步骤：
步骤301，基于目标手部图像，生成目标手部三维模型。
在一些实施例中，目标手部三维模型可以是，具有目标手部图像中手部特征的三维模型。
在一些实施例中，可以将目标手部图像传入到神经网络生成具有手部特征的数据，之后将具有手部特征的数据传入渲染引擎，经过渲染引擎的渲染得到目标手部三维模型。也可以是通过测量手部得到具有手部特征数 据，将具有手部特征的数据输入到渲染引擎进行渲染，得到目标手部三维模型。
在一些实施例一些可选的实现方式中，基于上述目标手部图像生成三维手部关键点。可以将目标手部图像传入到预先训练的密集卷积网络(DenseNet)，将密集卷积网络(DenseNet)输出的三维坐标，作为三维手部关键点。利用三维渲染引擎对上述三维手部关键点进行渲染，将三维手部关键点进行平滑连接和三维模型填充，得到目标手部三维模型。
在一些实施例一些可选的实现方式中，可以将目标手部图像传入到预先训练的三维点云网络(PointNet)，三维点云网络(PointNet)输出三维点集合。使用三维点集合中的关键点集合，确定与目标手部图像适配的手部关节点位置系数和手部形状系数。利用三维渲染引擎，使用上述手部关节点位置系数和手部形状系数，来调节三维渲染引擎预先获取到的初始手部三维模型。三维渲染引擎将调节后输出的模型为目标手部三维模型。其中，上述手部关节点位置系数可以控制目标手部三维模型的动作，手部形状系数可以控制目标手部三维模型的各个关节长度和手部各个部分的形状大小。
步骤302，将上述目标手部三维模型和手部装饰品三维模型组合，得到上述包含手部装饰品的手部三维模型。
在一些实施例一些可选的实现方式中，可以将上述目标手部三维模型的手指三维模型，与预先得到的手部装饰品三维模型组合。
进一步参考图4，图4是根据本公开一些实施例的图像生成方法的中步骤301和302的应用场景的示意图400。
如图4所示，基于目标手部图像402，生成目标手部三维模型405，其中，计算设备401可以将目标手部图像402传入到可以生成三维手部关键点的神经网络403，从而得到三维手部关键点404。将上述三维手部关键点404进行连接和渲染，生成目标手部三维模型405。将目标手部三维模型405和手部装饰品三维模型406组合，得到上述包含手部装饰品的手部三维模型407。
步骤303，对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合。
步骤304，对上述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，得到手部装饰品图像。
步骤305，将上述手部装饰品图像和上述目标手部图像进行组合，得到包括手部装饰品的手部图像。
在一些实施例中，步骤303、304和305的具体实现及其所带来的技术效果，可以参考图2对应的实施例中的步骤201、202和203，在此不再赘述。
本公开的一些实施例公开的图像生成方法，与图2对应的那些实施例相比，增加了生成包含手部装饰品的手部三维模型的步骤。其中，基于目标手部图像可以生成与手部准确适配的三维模型。从而使得使得呈现出的穿戴效果更准确。
进一步参考图5，作为对上述各图所示方法的实现，本公开提供了一种图像生成装置的一些实施例，这些装置实施例与图2所示的那些方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图5所示，一些实施例的图像生成装置500包括：模型调整单元501，被配置成对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合。模型渲染单元502，被配置成对上述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，得到手部装饰品图像。图像组合单元503，被配置成将上述手部装饰品图像和上述目标手部图像进行组合，得到包括手部装饰品的手部图像。
在一些实施例的可选实现方式中，上述装置500还包括：模型生成单元，被配置成基于上述目标手部图像，生成目标手部三维模型；模型组合单元，被配置成将上述目标手部三维模型和手部装饰品三维模型组合，得到上述包含手部装饰品的手部三维模型。
在一些实施例的可选实现方式中，模型生成单元进一步被配置成：基于目标手部图像生成三维手部关键点；基于上述三维手部关键点，生成上述目标手部三维模型。
在一些实施例的可选实现方式中，模型生成单元还可以进一步被配置成：确定上述目标手部图像的目标系数；基于上述目标系数，调节预先获 取到的初始手部三维模型，得到上述目标手部三维模型。
在一些实施例的可选实现方式中，上述目标系数，包括：上述目标手部图像表征的手部关节点位置系数和手部形状系数。
在一些实施例的可选实现方式中，模型调整单元501进一步被配置成：将上述包含手部装饰品的手部三维模型进行旋转或平移。
可以理解的是，该装置500中记载的诸单元与参考图2描述的方法中的各个步骤相对应。由此，上文针对方法描述的操作、特征以及产生的有益效果同样适用于装置500及其中包含的单元，在此不再赘述。
如图6所示，电子设备600可以包括处理装置(例如中央处理器、图形处理器等)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储装置608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有电子设备600操作所需的各种程序和数据。处理装置601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
通常，以下装置可以连接至I/O接口605：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置606；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置607；包括例如磁带、硬盘等的存储装置608；以及通信装置609。通信装置609可以允许电子设备600与其他设备进行无线或有线通信以交换数据。虽然图6示出了具有各种装置的电子设备600，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。图6中示出的每个方框可以代表一个装置，也可以根据需要代表多个装置。
特别地，根据本公开的一些实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的一些实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的一些实施例中，该计算机程序可以通过通信装置609从网络上被下载和安装，或者从存储装置608被安装，或者从ROM 602被安装。在该计算机程序被处理装置601执行时，执行本公开的一些实施例的方法中限定的上述功能。
需要说明的是，本公开的一些实施例所述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开的一些实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。而在本公开的一些实施例中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合；对上述与目标手部图像适配的三维模型组合中的手部装饰 品三维模型进行渲染，得到手部装饰品图像；将上述手部装饰品图像和上述目标手部图像进行组合，得到包括手部装饰品的手部图像。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的一些实施例的操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开的一些实施例中的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括配置模型调整单元、模型渲染单元和图像组合单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，模型调整单元还可以被描述为“对包含手部装饰品的手部三维模型进行调整的单元”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件 来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上***(SOC)、复杂可编程逻辑设备(CPLD)等等。
根据本公开的一个或多个实施例，提供了一种图像生成方法，包括：对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合；对上述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，得到手部装饰品图像；将上述手部装饰品图像和上述目标手部图像进行组合，得到包括手部装饰品的手部图像。
根据本公开的一个或多个实施例，在对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合之前，上述方法还包括：基于上述目标手部图像，生成目标手部三维模型；将上述目标手部三维模型和手部装饰品三维模型组合，得到上述包含手部装饰品的手部三维模型。
根据本公开的一个或多个实施例，上述基于上述目标手部图像，生成目标手部三维模型，包括：基于上述目标手部图像生成三维手部关键点；基于上述三维手部关键点，生成上述目标手部三维模型。
根据本公开的一个或多个实施例，上述基于上述目标手部图像，生成目标手部三维模型，包括：确定上述目标手部图像的目标系数；基于上述目标系数，调节预先获取到的初始手部三维模型，得到上述目标手部三维模型。
根据本公开的一个或多个实施例，上述目标系数，包括：上述目标手部图像表征的手部关节点位置系数和手部形状系数。
根据本公开的一个或多个实施例，上述对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合，包括：将上述包含手部装饰品的手部三维模型进行旋转或平移。
根据本公开的一个或多个实施例，图像生成装置包括：模型调整单元，被配置成对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合。模型渲染单元，被配置成对上述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，得到手部装饰品图像。图像组合单元，被配置成将上述手部装饰品图像和上述目标手部图 像进行组合，得到包括手部装饰品的手部图像。
根据本公开的一个或多个实施例，上述装置还包括：模型生成单元，被配置成基于上述目标手部图像，生成目标手部三维模型；模型组合单元，被配置成将上述目标手部三维模型和手部装饰品三维模型组合，得到上述包含手部装饰品的手部三维模型。
根据本公开的一个或多个实施例，模型生成单元进一步被配置成：基于目标手部图像生成三维手部关键点；基于上述三维手部关键点，生成上述目标手部三维模型。
根据本公开的一个或多个实施例，模型生成单元还可以进一步被配置成：确定上述目标手部图像的目标系数；基于上述目标系数，调节预先获取到的初始手部三维模型，得到上述目标手部三维模型。
根据本公开的一个或多个实施例，上述目标系数，包括：上述目标手部图像表征的手部关节点位置系数和手部形状系数。
根据本公开的一个或多个实施例，模型调整单元进一步被配置成：将上述包含手部装饰品的手部三维模型进行旋转或平移。
根据本公开的一个或多个实施例，提供了一种电子设备，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如上述任一的方法。
根据本公开的一个或多个实施例，提供了一种计算机可读介质，其上存储有计算机程序，其中，程序被处理器执行时实现如上述任一实施例描述的方法。
以上描述仅为本公开的一些较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开的实施例中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开的实施例中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (10)

  1. 一种图像生成方法，包括：
    对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合；
    对所述三维模型组合中的手部装饰品三维模型进行渲染，得到手部装饰品图像；
    将所述手部装饰品图像和所述目标手部图像进行组合，得到包括手部装饰品的手部图像。
  2. 根据权利要求1所述方法，其中，在对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合之前，所述方法还包括：
    基于所述目标手部图像，生成目标手部三维模型；
    将所述目标手部三维模型和手部装饰品三维模型组合，得到所述包含手部装饰品的手部三维模型。
  3. 根据权利要求2所述方法，其中，所述基于所述目标手部图像，生成目标手部三维模型，包括：
    基于所述目标手部图像生成三维手部关键点；
    基于所述三维手部关键点，生成所述目标手部三维模型。
  4. 根据权利要求2所述方法，其中，所述基于所述目标手部图像，生成目标手部三维模型，包括：
    确定所述目标手部图像的目标系数；
    基于所述目标系数，调节预先获取到的初始手部三维模型，得到所述目标手部三维模型。
  5. 根据权利要求4所述方法，其中，所述目标系数，包括：
    所述目标手部图像表征的手部关节点位置系数和手部形状系数。
  6. 根据权利要求1所述方法，其中，所述对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合，包括：
    将所述包含手部装饰品的手部三维模型进行旋转或平移。
  7. 一种图像生成的装置，包括：
    模型调整单元，被配置成对包含手部装饰品的手部三维模型进行调整，得到与目标手部图像适配的三维模型组合；
    模型渲染单元，被配置成对所述与目标手部图像适配的三维模型组合中的手部装饰品三维模型进行渲染，得到手部装饰品图像；
    图像组合单元，被配置成将所述手部装饰品图像和所述目标手部图像进行组合，得到包括手部装饰品的手部图像。
  8. 根据权利要求7所述装置，其中，所述装置还包括：
    模型生成单元，被配置成基于所述目标手部图像，生成目标手部三维模型；
    模型组合单元，被配置成将所述目标手部三维模型和手部装饰品三维模型组合，得到所述包含手部装饰品的手部三维模型。
  9. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-6中任一所述的方法。
  10. 一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1-6中任一所述的方法。
PCT/CN2021/109552 2020-10-21 2021-07-30 图像生成方法、装置、设备和计算机可读介质 WO2022083213A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011134814.6 2020-10-21
CN202011134814.6A CN112241999A (zh) 2020-10-21 2020-10-21 图像生成方法、装置、设备和计算机可读介质

Publications (1)

Publication Number Publication Date
WO2022083213A1 true WO2022083213A1 (zh) 2022-04-28

Family

ID=74169405

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/109552 WO2022083213A1 (zh) 2020-10-21 2021-07-30 图像生成方法、装置、设备和计算机可读介质

Country Status (2)

Country Link
CN (1) CN112241999A (zh)
WO (1) WO2022083213A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112241999A (zh) * 2020-10-21 2021-01-19 北京字跳网络技术有限公司 图像生成方法、装置、设备和计算机可读介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108447043A (zh) * 2018-03-30 2018-08-24 腾讯科技（深圳）有限公司 一种图像合成方法、设备及计算机可读介质
CN111368668A (zh) * 2020-02-25 2020-07-03 北京字节跳动网络技术有限公司 三维手部识别方法、装置、电子设备及存储介质
CN111754303A (zh) * 2020-06-24 2020-10-09 北京字节跳动网络技术有限公司 虚拟换服饰的方法和装置、设备和介质
CN112232183A (zh) * 2020-10-14 2021-01-15 北京字节跳动网络技术有限公司 虚拟佩戴物匹配方法、装置、电子设备和计算机可读介质
CN112241999A (zh) * 2020-10-21 2021-01-19 北京字跳网络技术有限公司 图像生成方法、装置、设备和计算机可读介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108447043A (zh) * 2018-03-30 2018-08-24 腾讯科技（深圳）有限公司 一种图像合成方法、设备及计算机可读介质
CN111368668A (zh) * 2020-02-25 2020-07-03 北京字节跳动网络技术有限公司 三维手部识别方法、装置、电子设备及存储介质
CN111754303A (zh) * 2020-06-24 2020-10-09 北京字节跳动网络技术有限公司 虚拟换服饰的方法和装置、设备和介质
CN112232183A (zh) * 2020-10-14 2021-01-15 北京字节跳动网络技术有限公司 虚拟佩戴物匹配方法、装置、电子设备和计算机可读介质
CN112241999A (zh) * 2020-10-21 2021-01-19 北京字跳网络技术有限公司 图像生成方法、装置、设备和计算机可读介质

Also Published As

Publication number Publication date
CN112241999A (zh) 2021-01-19

Similar Documents

Publication Publication Date Title
WO2022042290A1 (zh) 一种虚拟模型处理方法、装置、电子设备和存储介质
WO2022037602A1 (zh) 表情变换方法、装置、电子设备和计算机可读介质
US11776209B2 (en) Image processing method and apparatus, electronic device, and storage medium
WO2022078014A1 (zh) 虚拟佩戴物匹配方法、装置、电子设备和计算机可读介质
CN109754464B (zh) 用于生成信息的方法和装置
TWI718631B (zh) 人臉圖像的處理方法及裝置、電子設備和儲存介質
CN111932664A (zh) 图像渲染方法、装置、电子设备及存储介质
WO2021258971A1 (zh) 虚拟换服饰的方法和装置、设备和介质
WO2020211573A1 (zh) 用于处理图像的方法和装置
WO2023160513A1 (zh) 3d素材的渲染方法、装置、设备及存储介质
WO2023103999A1 (zh) 3d目标点渲染方法、装置、设备及存储介质
CN113806306B (zh) 媒体文件处理方法、装置、设备、可读存储介质及产品
WO2022233223A1 (zh) 图像拼接方法、装置、设备及介质
WO2023051244A1 (zh) 图像生成方法、装置、设备及存储介质
WO2023125365A1 (zh) 图像处理方法、装置、电子设备及存储介质
WO2023138498A1 (zh) 生成风格化图像的方法、装置、电子设备及存储介质
WO2023029893A1 (zh) 纹理映射方法、装置、设备及存储介质
CN110349107A (zh) 图像增强的方法、装置、电子设备、及存储介质
WO2022083213A1 (zh) 图像生成方法、装置、设备和计算机可读介质
WO2024094158A1 (zh) 特效处理方法、装置、设备及存储介质
WO2021227953A1 (zh) 图像特效配置方法、图像识别方法、装置及电子设备
CN110248197B (zh) 语音增强方法及装置
WO2024055837A1 (zh) 一种图像处理方法、装置、设备及介质
CN115775310A (zh) 数据处理方法、装置、电子设备和存储介质
WO2023193613A1 (zh) 高光渲染方法、装置、介质及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21881633

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21881633

Country of ref document: EP

Kind code of ref document: A1