CN110288532B - Method, apparatus, device and computer readable storage medium for generating whole body image - Google Patents
Method, apparatus, device and computer readable storage medium for generating whole body image Download PDFInfo
- Publication number
- CN110288532B CN110288532B CN201910585873.6A CN201910585873A CN110288532B CN 110288532 B CN110288532 B CN 110288532B CN 201910585873 A CN201910585873 A CN 201910585873A CN 110288532 B CN110288532 B CN 110288532B
- Authority
- CN
- China
- Prior art keywords
- body image
- whole
- target object
- key points
- gesture
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012545 processing Methods 0.000 claims description 27
- 238000010586 diagram Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 6
- 238000013528 artificial neural network Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000008485 antagonism Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
Embodiments of the present disclosure provide a method, apparatus, device, and computer-readable storage medium for generating a whole-body image, the method comprising: acquiring a half-body image of a target object; inputting the half-body image into a preset network to obtain a first whole-body image of the target object; determining key points of the gesture of the target object; inputting the key points of the first whole-body image and the gesture of the target object into a preset network, correcting the key points of the first whole-body image, and determining a second whole-body image of the target object. According to the method, the half body image of the target object is supplemented to the first whole body image, then the first whole body image and the key points of the gesture of the target object are input to a preset network to obtain the second whole body image, the complexity of generating the whole body image by the half body image in one step can be reduced, the effect of generating the second whole body image is good, and the user experience is improved.
Description
Technical Field
The present disclosure relates to the field of computer technology, and in particular, to a method, apparatus, device, and computer readable storage medium for generating whole-body images.
Background
The artificial neural networks (Artificial Neural Networks, ANNs) are called Neural Networks (NNs) or Connection models (Connection models) for short, are algorithm mathematical models for simulating the behavior characteristics of animal neural networks and performing distributed parallel information processing, in the prior art, the whole body image of a person and the gesture information of the person to be generated are obtained through the neural networks, the complexity is high, the effect of the generated whole body image is poor, and the user experience is poor.
Disclosure of Invention
The present disclosure addresses the shortcomings of the existing approaches by providing a method, apparatus, device, and computer-readable storage medium for generating a whole-body image, which are used to solve the problem of how to reduce the complexity of generating a whole-body image from a half-body image, and at the same time achieve a good generation effect of the whole-body image.
In a first aspect, the present disclosure provides a method of generating a whole-body image, comprising:
acquiring a half-body image of a target object;
inputting the half-body image into a preset network to obtain a first whole-body image of the target object;
determining key points of the gesture of the target object;
inputting the key points of the first whole-body image and the gesture of the target object into a preset network, correcting the key points of the first whole-body image, and determining a second whole-body image of the target object.
Optionally, inputting the half-body image into a preset network to obtain a first whole-body image of the target object, including:
the half-body image is input to a generated countermeasure network GAN, and a first whole-body image is determined.
Optionally, determining the keypoints of the pose of the target object includes:
splicing the first whole body image and a thermodynamic diagram of the Heatmap to obtain the splice of the Heatmap image, wherein the thermodynamic diagram is used for representing the distribution of key points of the gesture of the target object;
and determining key points of the gesture according to the concatenation of the hematmap images.
Optionally, determining the key point of the pose according to the stitching of the hectmap images includes:
determining information of key points of each part area of the target object according to the concatenation of the hematmap images;
and determining the key points of the gesture according to the information of the key points of each part area of the target object.
Optionally, inputting the first whole-body image and the key points of the gesture of the target object to a preset network, correcting the key points of the first whole-body image, and determining the second whole-body image of the target object, including:
and inputting the key points of the first whole-body image and the gesture of the target object to the GAN, correcting the key points of the first whole-body image, and generating a second whole-body image corresponding to the key points of the gesture.
In a second aspect, the present disclosure provides an apparatus for generating a whole-body image, comprising:
the first processing module is used for acquiring a half-body image of the target object;
the second processing module is used for inputting the half-body image into a preset network to obtain a first whole-body image of the target object;
the third processing module is used for determining key points of the gesture of the target object;
the fourth processing module is used for inputting the key points of the first whole-body image and the gesture of the target object to a preset network, correcting the key points of the first whole-body image and determining the second whole-body image of the target object.
The second processing module is used for inputting the half body image into the generated countermeasure network GAN and determining the first whole body image.
The third processing module is further used for splicing the first whole-body image and the thermodynamic diagram hematmap to obtain the splicing of the hematmap images, and the thermodynamic diagram is used for representing the distribution of key points of the gesture of the target object; and determining key points of the gesture according to the concatenation of the hematmap images.
In a third aspect, the present disclosure provides an electronic device comprising: a processor, a memory, and a bus;
a bus for connecting the processor and the memory;
a memory for storing operation instructions;
and a processor for executing the method of generating a whole-body image of the first aspect of the present disclosure by invoking the operation instruction.
In a fourth aspect, the present disclosure provides a computer-readable storage medium storing a computer program for performing the method of generating a whole-body image of the first aspect of the present disclosure.
The technical scheme provided by the embodiment of the disclosure has at least the following beneficial effects:
acquiring a half-body image of a target object; inputting the half-body image into a preset network to obtain a first whole-body image of the target object; determining key points of the gesture of the target object; inputting the key points of the first whole-body image and the gesture of the target object into a preset network, correcting the key points of the first whole-body image, and determining a second whole-body image of the target object. Therefore, the half body image of the target object is supplemented to the first whole body image, then the first whole body image and the key points of the gesture of the target object are input to the preset network to obtain the second whole body image, the complexity of generating the whole body image by the half body image in one step can be reduced, the effect of generating the second whole body image is good, and the user experience is improved.
Additional aspects and advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings that are required to be used in the description of the embodiments of the present disclosure will be briefly introduced below.
FIG. 1 is a flow chart of a method of generating a whole-body image according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of an apparatus for generating a whole-body image according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of illustrating the present disclosure and are not to be construed as limiting the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification of this disclosure, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The following describes the technical solutions of the present disclosure and how the technical solutions of the present disclosure solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present disclosure will be described below with reference to the accompanying drawings.
Example 1
In an embodiment of the present disclosure, a method for generating a whole-body image is provided, a flow chart of the method is shown in fig. 1, and the method includes:
s101, acquiring a half-body image of a target object.
Optionally, a half-body image of the pose of the human body is acquired.
S102, inputting the half-body image into a preset network to obtain a first whole-body image of the target object.
Optionally, inputting the half-body image into a preset network to obtain a first whole-body image of the target object, including:
the half-body image is input to a generated countermeasure network GAN, and a first whole-body image is determined.
Alternatively, the generative antagonism network (GAN, generative Adversarial Networks) is a deep learning model, which is one of the methods of unsupervised learning over complex distributions. The model is built up of (at least) two modules in a frame: the mutual game learning of the Generative Model G network and the discriminant Model (Discriminative Model) D network produces a fairly good output. Deep neural networks are commonly used in practice as G-networks and D-networks. The G network is used for generating an image, and after a random code is input, the G network outputs a fake image automatically generated by the neural network; the D network is used for judging, the D network takes the image output by the G network as input, and then judges the true or false of the image, true output 1 and false output 0. The G network is mainly used for learning the real image distribution so as to lead the image generated by the G network to be more real and cheat the D network; the D network needs to determine whether the received image is true or false. In the whole process, the G network strives to make the generated image more real, and the D network strives to identify the true or false of the image, the process is equivalent to a two-player game, and as time goes on, the G network and the D network continuously fight, and finally the two networks achieve a dynamic balance: the G network generates an image that is distributed close to the real image, whereas the D network does not recognize the real and false images. For example, the GAN is applied to a deep learning neural network, and the G network and the D network are used to continuously game, so that the G network learns the data distribution, and if the GAN is used to generate an image, the G network can generate a realistic image from a section of random number after the training is completed.
Optionally, the preset network is one of GAN; the preset network can synthesize 2048 x 1024 images with high definition, and the preset network uses a G network from coarse to fine and a multi-scale D network. The preset network can generate high-resolution and high-quality images. The preset network takes the low-resolution image output first, takes the low-resolution image output before as the input of another network, and then generates the image with higher resolution.
Optionally, the input of the preset network is a whole body image, and the supervision output of the preset network is a first whole body image, so that the first whole body image can be generated through the preset network, that is, the first whole body image is complemented through the whole body image.
S103, determining key points of the gesture of the target object.
Optionally stitching the first whole-body image with a thermodynamic diagram of the hetmap, resulting in stitching of the hetmap images, the thermodynamic diagram being used to characterize the distribution of key points of the pose of the target object;
and determining key points of the gesture according to the concatenation of the hematmap images.
Optionally, determining the key point of the pose according to the stitching of the hectmap images includes:
determining information of key points of each part area of the target object according to the concatenation of the hematmap images;
and determining the key points of the gesture according to the information of the key points of each part area of the target object.
Optionally, stitching the first whole-body image with the thermodynamic diagram Heatm to obtain stitching of the Heatm image, wherein H is W3 is the size of the first whole-body image, H is W1 is the size of the thermodynamic diagram Heatm, and H is W4 is stitching of the Heatm image; specifically, H and W in the h×w×d matrix represent the height and width of the image, D represents the dimension (channel number) of the feature vector extracted by each pixel in the image, and the color model RGB of the first whole-body image is three-dimensional, so that a D value of 3 in the size h×w×3 of the first whole-body image represents three-dimensional; the thermodynamic diagram Heatm is one-dimensional, so that the value of D in the size H.times.W.times.1 of the thermodynamic diagram Heatm is 1 to represent one dimension; splice H x W x 4 of the hematmap image with D value 4 indicates four channels. The size of the thermodynamic diagram is consistent with that of the target object, the thermodynamic diagram can generate a probability area of Gaussian distribution in the area where the key points of the gesture of the target object are located, the central value of the area where the key points of the gesture of the target object are located is maximum, the closest to 1, and the probability is smaller as the surrounding is. Thermodynamic diagrams of the heat map may intuitively present some data that would otherwise be unintelligible or expressive, such as density, frequency, temperature, etc., in a more easily understood manner, by changing the area and color. From the hetmap of the image, it is possible to detect a key point of the pose of the target object, for example, a region of the face has a red region, which is a region where the key point of the face is located.
S104, inputting key points of the first whole-body image and the gesture of the target object into a preset network, correcting the key points of the first whole-body image, and determining a second whole-body image of the target object.
Optionally, inputting the first whole-body image and the key points of the gesture of the target object to a preset network, correcting the key points of the first whole-body image, and determining the second whole-body image of the target object, including:
and inputting the key points of the first whole-body image and the gesture of the target object to the GAN, correcting the key points of the first whole-body image, and generating a second whole-body image corresponding to the key points of the gesture.
The application of the embodiment of the disclosure has at least the following beneficial effects:
acquiring a half-body image of a target object; inputting the half-body image into a preset network to obtain a first whole-body image of the target object; determining key points of the gesture of the target object; inputting the key points of the first whole-body image and the gesture of the target object into a preset network, correcting the key points of the first whole-body image, and determining a second whole-body image of the target object. Therefore, the half body image of the target object is supplemented to the first whole body image, then the first whole body image and the key points of the gesture of the target object are input to the preset network to obtain the second whole body image, the complexity of generating the whole body image by the half body image in one step can be reduced, the effect of generating the second whole body image is good, and the user experience is improved.
Example two
Based on the same inventive concept, the embodiment of the present disclosure further provides an apparatus for generating a whole-body image, where a schematic structural diagram of the apparatus is shown in fig. 2, and the apparatus 20 for generating a whole-body image includes a first processing module 201, a second processing module 202, a third processing module 203, and a fourth processing module 204.
A first processing module 201, configured to acquire a half-body image of a target object;
the second processing module 202 is configured to input the half-body image into a preset network to obtain a first whole-body image of the target object;
a third processing module 203, configured to determine a keypoint of the pose of the target object;
the fourth processing module 204 is configured to input the key points of the first whole-body image and the gesture of the target object to a preset network, correct the key points of the first whole-body image, and determine a second whole-body image of the target object.
Optionally, the second processing module 202 is specifically configured to input the half-body image into the generated countermeasure network GAN, and determine the first whole-body image.
Optionally, the third processing module 203 is specifically configured to stitch the first whole-body image and the thermodynamic diagram hematmap to obtain stitch of the hematmap image; and determining key points of the gesture according to the concatenation of the hematmap images.
Optionally, the third processing module 203 is specifically configured to determine information of key points of each part area of the target object according to stitching of the hematmap images; and determining the key points of the gesture according to the information of the key points of each part area of the target object.
Optionally, the fourth processing module 204 is specifically configured to input the first whole-body image and the key point of the gesture of the target object to the GAN, correct the key point of the first whole-body image, and generate a second whole-body image corresponding to the key point of the gesture.
The device for generating a whole-body image according to the embodiment of the present disclosure may refer to the method for generating a whole-body image according to the first embodiment, and the beneficial effects that the device for generating a whole-body image according to the embodiment of the present disclosure can achieve are the same as the method for generating a whole-body image according to the first embodiment, and are not described herein again.
The application of the embodiment of the disclosure has at least the following beneficial effects:
acquiring a half-body image of a target object; inputting the half-body image into a preset network to obtain a first whole-body image of the target object; determining key points of the gesture of the target object; inputting the key points of the first whole-body image and the gesture of the target object into a preset network, correcting the key points of the first whole-body image, and determining a second whole-body image of the target object. Therefore, the half body image of the target object is supplemented to the first whole body image, then the first whole body image and the key points of the gesture of the target object are input to the preset network to obtain the second whole body image, the complexity of generating the whole body image by the half body image in one step can be reduced, the effect of generating the second whole body image is good, and the user experience is improved.
Example III
Based on the same principles as the method of generating a whole-body image in embodiments of the present disclosure, the present disclosure provides an electronic device comprising a processor and a memory; a memory for storing operation instructions; a processor for executing the method as shown in any one of the embodiments of the method of generating a whole-body image of the present disclosure by invoking the operation instructions.
Based on the same principles as the methods of generating a whole-body image in the embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set that is loaded and executed by a processor to implement the method as shown in any one of the methods of generating a whole-body image of the present disclosure.
In an example, as shown in fig. 3, a schematic diagram of a structure of an electronic device 800 suitable for use in implementing embodiments of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 3, the electronic device 800 may include a processing means (e.g., a central processor, a graphics processor, etc.) 801, which may perform various appropriate actions and processes according to programs stored in a Read Only Memory (ROM) 802 or programs loaded from a storage 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.
In general, the following devices may be connected to the I/O interface 805: input devices 806 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 807 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, etc.; storage 808 including, for example, magnetic tape, hard disk, etc.; communication means 809. The communication means 809 may allow the electronic device 800 to communicate wirelessly or by wire with other devices to exchange data. While fig. 3 shows an electronic device 800 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication device 809, or installed from storage device 808, or installed from ROM 802. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 801.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to perform the method shown in the method embodiments described above; alternatively, the computer-readable medium carries one or more programs, which when executed by the electronic device, cause the electronic device to perform the method shown in the method embodiments.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language 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. In the case of a remote computer, 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 (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block 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. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The name of the unit does not in any way constitute a limitation of the unit itself, for example the first acquisition unit may also be described as "unit acquiring at least two internet protocol addresses".
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).
Claims (8)
1. A method of generating a whole-body image, comprising:
acquiring a half-body image of a target object;
inputting the half-body image into a preset network to obtain a first whole-body image of the target object;
determining key points of the gesture of the target object;
inputting key points of the first whole-body image and the gesture of the target object into the preset network, correcting the key points of the first whole-body image, and determining a second whole-body image of the target object;
wherein the determining the key point of the gesture of the target object includes:
stitching the first whole-body image with a thermodynamic diagram of a hetmap, so as to obtain stitching of the hetmap image, wherein the thermodynamic diagram is used for representing the distribution of key points of the gesture of the target object;
and determining key points of the gesture according to the concatenation of the hematmap images.
2. The method of claim 1, wherein said inputting the whole-body image into a preset network results in a first whole-body image of the target object, comprising:
the half-body image is input to a generated countermeasure network GAN, and the first whole-body image is determined.
3. The method of claim 1, wherein the determining key points of the pose from stitching of the hetmap images comprises:
determining information of key points of each part area of the target object according to the concatenation of the hematmap images;
and determining the key points of the gesture according to the information of the key points of each part area of the target object.
4. The method according to claim 1, wherein inputting the key points of the first whole-body image and the pose of the target object to the preset network, correcting the key points of the first whole-body image, and determining the second whole-body image of the target object includes:
inputting the key points of the first whole-body image and the gesture of the target object to a GAN, correcting the key points of the first whole-body image, and generating the second whole-body image corresponding to the key points of the gesture.
5. An apparatus for generating a whole-body image, comprising:
the first processing module is used for acquiring a half-body image of the target object;
the second processing module is used for inputting the half-body image into a preset network to obtain a first whole-body image of the target object;
a third processing module, configured to determine a keypoint of the gesture of the target object;
the fourth processing module is used for inputting the key points of the first whole-body image and the gesture of the target object into the preset network, correcting the key points of the first whole-body image and determining a second whole-body image of the target object;
the third processing module is further configured to stitch the first whole-body image and a thermodynamic diagram hematmap to obtain stitch of the hematmap image, where the thermodynamic diagram is used for representing distribution of key points of the gesture of the target object; and determining key points of the gesture according to the concatenation of the hematmap images.
6. The apparatus according to claim 5, comprising:
the second processing module is configured to input the half-body image into a generated countermeasure network GAN, and determine the first whole-body image.
7. An electronic device, comprising: a processor, a memory;
the memory is used for storing a computer program;
the processor for executing the method of generating a whole-body image according to any of the preceding claims 1-4 by invoking the computer program.
8. A computer-readable storage medium, characterized in that a computer program is stored for implementing the method of generating a whole-body image according to any one of claims 1-4 when being executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910585873.6A CN110288532B (en) | 2019-07-01 | 2019-07-01 | Method, apparatus, device and computer readable storage medium for generating whole body image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910585873.6A CN110288532B (en) | 2019-07-01 | 2019-07-01 | Method, apparatus, device and computer readable storage medium for generating whole body image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110288532A CN110288532A (en) | 2019-09-27 |
| CN110288532B true CN110288532B (en) | 2023-08-08 |
Family
ID=68021574
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910585873.6A Active CN110288532B (en) | 2019-07-01 | 2019-07-01 | Method, apparatus, device and computer readable storage medium for generating whole body image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288532B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111292365B (en) * | 2020-01-23 | 2023-07-25 | 抖音视界有限公司 | Method, apparatus, electronic device and computer readable medium for generating depth map |
| CN111553324B (en) * | 2020-05-22 | 2023-05-23 | 北京字节跳动网络技术有限公司 | Human body posture predicted value correction method, device, server and storage medium |
| CN114332334A (en) * | 2021-12-31 | 2022-04-12 | 中国电信股份有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108564119A (en) * | 2018-04-04 | 2018-09-21 | 华中科技大学 | A kind of any attitude pedestrian Picture Generation Method |
| CN109443101A (en) * | 2018-12-29 | 2019-03-08 | 河北砺兵科技有限责任公司 | A kind of more target multi-pose display devices of robot target and training method |
| CN109697446A (en) * | 2018-12-04 | 2019-04-30 | 北京字节跳动网络技术有限公司 | Image key points extracting method, device, readable storage medium storing program for executing and electronic equipment |
| CN109934111A (en) * | 2019-02-12 | 2019-06-25 | 清华大学深圳研究生院 | A kind of body-building Attitude estimation method and system based on key point |
| CN109934165A (en) * | 2019-03-12 | 2019-06-25 | 南方科技大学 | A kind of joint point detecting method, device, storage medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214980B (en) * | 2017-07-04 | 2023-06-23 | 阿波罗智能技术(北京)有限公司 | Three-dimensional attitude estimation method, three-dimensional attitude estimation device, three-dimensional attitude estimation equipment and computer storage medium |
-
2019
- 2019-07-01 CN CN201910585873.6A patent/CN110288532B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108564119A (en) * | 2018-04-04 | 2018-09-21 | 华中科技大学 | A kind of any attitude pedestrian Picture Generation Method |
| CN109697446A (en) * | 2018-12-04 | 2019-04-30 | 北京字节跳动网络技术有限公司 | Image key points extracting method, device, readable storage medium storing program for executing and electronic equipment |
| CN109443101A (en) * | 2018-12-29 | 2019-03-08 | 河北砺兵科技有限责任公司 | A kind of more target multi-pose display devices of robot target and training method |
| CN109934111A (en) * | 2019-02-12 | 2019-06-25 | 清华大学深圳研究生院 | A kind of body-building Attitude estimation method and system based on key point |
| CN109934165A (en) * | 2019-03-12 | 2019-06-25 | 南方科技大学 | A kind of joint point detecting method, device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110288532A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109902659B (en) | Method and apparatus for processing human body image | |
| CN112766189B (en) | Deep forgery detection method and device, storage medium and electronic equipment | |
| CN109829432B (en) | Method and apparatus for generating information | |
| CN110288532B (en) | Method, apparatus, device and computer readable storage medium for generating whole body image | |
| CN111275784B (en) | Method and device for generating image | |
| CN109754464B (en) | Method and apparatus for generating information | |
| CN110069191B (en) | Terminal-based image dragging deformation implementation method and device | |
| CN110072047B (en) | Image deformation control method and device and hardware device | |
| CN111598168B (en) | Image classification method, device, computer equipment and medium | |
| WO2020253716A1 (en) | Image generation method and device | |
| CN110035271B (en) | Fidelity image generation method and device and electronic equipment | |
| CN111368668B (en) | Three-dimensional hand recognition method and device, electronic equipment and storage medium | |
| CN114004905B (en) | Method, device, equipment and storage medium for generating character style pictogram | |
| CN113344776B (en) | Image processing method, model training method, device, electronic equipment and medium | |
| CN114693876A (en) | Digital human generation method, device, storage medium and electronic equipment | |
| CN110059739B (en) | Image synthesis method, image synthesis device, electronic equipment and computer-readable storage medium | |
| CN109829431A (en) | Method and apparatus for generating information | |
| CN110619602B (en) | Image generation method and device, electronic equipment and storage medium | |
| CN109816791B (en) | Method and apparatus for generating information | |
| CN110060324B (en) | Image rendering method and device and electronic equipment | |
| CN116681765A (en) | Method for determining identification position in image, method for training model, device and equipment | |
| CN116596748A (en) | Image stylization processing method, apparatus, device, storage medium, and program product | |
| CN115880526A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN110942033B (en) | Method, device, electronic equipment and computer medium for pushing information | |
| CN116527993A (en) | Video processing method, apparatus, electronic device, storage medium and program product |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Applicant after: Douyin Vision Co.,Ltd. Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Applicant before: Tiktok vision (Beijing) Co.,Ltd. Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Applicant after: Tiktok vision (Beijing) Co.,Ltd. Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Applicant before: BEIJING BYTEDANCE NETWORK TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |