Image processing method, display method and computing device

By integrating the face and body image models, the target human model is generated, which solves the problem of poor display effects of existing three-dimensional human image, and achieves a more realistic and accurate user image restoration.

WO2024240180A1PCT designated stage expired Publication Date: 2024-11-28HANGZHOU ALIBABA INT INTERNET IND CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/094678
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-23
Filing Date
2024-05-22
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

The existing three-dimensional human body images have poor visual display effect and lack relevance to users, so they cannot effectively restore the user's face image and body shape system.

Method used

The face geometric model and texture map are generated based on the face area and human body area images of the target user, and fuse it into the human body geometric model and texture map to generate the target human body model, which is used to render three-dimensional human body images and improve the authenticity and accuracy of the image. .

Benefits of technology

Effectively restore the user's face image and body shape system, significantly improving the display effect and authenticity of three-dimensional human image.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024094678_28112024_PF_FP_ABST
    Figure CN2024094678_28112024_PF_FP_ABST
Patent Text Reader

Abstract

The embodiments of the present application provide an image processing method, a display method and a computing device. The image processing method comprises: generating a facial geometric model and a facial texture map on the basis of at least one first image comprising a facial area of a target user; generating a human body geometric model on the basis of at least one second image comprising a human body area of the target user; fusing the facial geometric model into the human body geometric model to generate a target human body geometric model; fusing the facial texture map into a human body texture map to generate a target texture map; and obtaining a target human body model on the basis of the target texture map and the target human body geometric model, wherein the target human body model is used for rendering and generating a three-dimensional human body image of the target user. The technical solution provided in the embodiments of the present application improves the display effect of a three-dimensional human body image.
Need to check novelty before this filing date? Find Prior Art

Description

Image processing method, display method and computing device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on May 23, 2023, with application number 202310608672.X and application name “Image processing method, display method and computing device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of the present application relate to the field of computer application technology, and in particular to an image processing method, a display method, and a computing device. Background Art

[0003] In some application scenarios, users can record their body data online or obtain it through intelligent detection methods. This data can then be displayed to users for easy viewing. For example, in online shopping scenarios, size information is provided for wearable items such as clothing products. Users can select appropriate clothing products based on their body data and the size information. To enhance the display effect, a 3D human image can also be displayed. However, this 3D human image is not relevant to the user and the visual display effect is poor.

[0004] Summary of the Invention

[0005] The embodiments of the present application provide an image processing method, a display method, and a computing device to solve the problem of poor visual display effect of three-dimensional human body images in the prior art.

[0006] In a first aspect, an embodiment of the present application provides an image processing method, comprising:

[0007] generating a face geometry model and a face texture map based on at least one first image including a face region of a target user;

[0008] generating a human body geometric model based on at least one second image including a human body region of the target user;

[0009] fusing the face geometric model into the body geometric model to generate a target body geometric model;

[0010] Merging the face texture map into the body texture map to generate a target texture map;

[0011] A target human body model is obtained based on the target texture map and the target human body geometric model; the target human body model is used to render and generate a three-dimensional human body image of the target user.

[0012] Optionally, generating a facial geometric model and a facial texture map based on the at least one first image includes:

[0013] Performing three-dimensional reconstruction on the at least one first image to obtain a face geometric model;

[0014] Performing texture sampling based on the at least one first image and the face geometric model to obtain a first texture map corresponding to the facial area;

[0015] The first texture map is merged with the second texture map corresponding to the non-facial area to obtain a facial texture map.

[0016] Optionally, performing three-dimensional reconstruction on the at least one first image to obtain a facial geometric model includes:

[0017] The at least one first image is three-dimensionally reconstructed using a parameterized model to obtain a facial geometric model and the second texture map.

[0018] Optionally, generating a facial geometric model and a facial texture map based on the at least one first image includes:

[0019] Performing cartoon processing on the at least one first image to generate at least one cartoon face image;

[0020] A facial geometry model and a facial texture map are generated based on the at least one cartoon facial image.

[0021] Optionally, it also includes:

[0022] Based on the at least one first image, identifying a hairstyle category corresponding to the target user;

[0023] Determining a hairstyle texture map and a hairstyle geometric model corresponding to the hairstyle category;

[0024] The step of fusing the face geometric model with the body geometric model to generate a target body geometric model comprises:

[0025] fusing the hairstyle geometric model and the face geometric model into the body geometric model to generate a target body geometric model;

[0026] The step of fusing the face texture map into the body texture map to generate a target texture map comprises:

[0027] The hairstyle texture map and the face texture map are fused into the body texture map to generate a target texture map.

[0028] Optionally, after obtaining the target human body model, the method further includes:

[0029] The skeletal animation corresponding to the target human body model is determined; the target human body model is used to generate a dynamically changing three-dimensional human body image in combination with the skeletal animation rendering.

[0030] Optionally, it also includes:

[0031] The human body texture map is selected from at least one preset human body texture map template.

[0032] Optionally, it also includes:

[0033] A second texture map corresponding to the non-face area is determined from at least one preset non-face texture map template.

[0034] Optionally, identifying the hairstyle category corresponding to the target user based on the at least one first image includes:

[0035] Using a recognition model, based on the at least one first image, identifying a hairstyle category corresponding to the target user;

[0036] The recognition model is pre-trained based on the sample first image and its corresponding hairstyle category.

[0037] Optionally, it also includes:

[0038] At least one first image including a face area and at least one second image including a body area provided by a user are acquired.

[0039] In a second aspect, an embodiment of the present application provides a display method, including:

[0040] Displaying a three-dimensional human body image generated by rendering based on a target human body model;

[0041] The target human body model is generated based on a target texture map and a target human body geometry model. The target human body geometry model is obtained by fusing a facial geometry model into a human body geometry model. The target texture map is obtained by fusing a facial texture map into a human body texture map. The facial geometry model and the facial texture map are generated based on at least one first image including a facial area of ​​a target user. The human body geometry model is generated based on at least one second image including a human body area of ​​the target user.

[0042] Optionally, it also includes:

[0043] Obtain the target human body model sent by the server;

[0044] The three-dimensional human body image is generated based on the target human body model rendering.

[0045] Optionally, it also includes:

[0046] Capturing a frontal face area of ​​a target user from at least one angle to obtain at least one first image;

[0047] Capturing a human body region of the target user from at least one angle to obtain at least one second image;

[0048] The at least one first image and the at least one second image are sent to a server.

[0049] Optionally, it also includes:

[0050] Determining at least one object matching the target user;

[0051] displaying object prompt information of the at least one object;

[0052] In response to a triggering operation of the target user on the object prompt information, determining a corresponding target object;

[0053] A fused image of the object image of the target object and the three-dimensional human body image is displayed.

[0054] Optionally include:

[0055] Display trial prompt information on the target object's object details page;

[0056] In response to a triggering operation on the trial prompt information, obtaining the target human body model;

[0057] The three-dimensional human body image is generated based on the object image of the target object and the target human body model.

[0058] Optionally, it also includes:

[0059] Capturing an image of a target user from at least one angle to obtain at least one human body image;

[0060] identifying a face region and a body region from the at least one body image;

[0061] using at least one human body image including the face region as a first image;

[0062] At least one human body image including the human body region is used as a second image.

[0063] Optionally, it also includes:

[0064] Acquire human body data identifying the target user in the at least one second image;

[0065] The human body data is displayed at a corresponding characteristic position in the three-dimensional human body image.

[0066] Optionally, it also includes:

[0067] detecting a first interactive operation on the three-dimensional human body image;

[0068] The three-dimensional human body image is rotated and the rotated three-dimensional human body image is displayed.

[0069] Optionally, rotating the three-dimensional human body image and displaying the rotated three-dimensional human body image includes:

[0070] The three-dimensional human body image is rotated in a preset rotation direction with the vertical direction as the touch point position changes, and the rotated three-dimensional human body image is displayed after the first interactive operation is completed.

[0071] Optionally, it also includes:

[0072] detecting a second interactive operation on the three-dimensional human body image;

[0073] The three-dimensional human body image is switched and displayed as a partial human body image, and a corresponding dynamically changing image is displayed during the switching process.

[0074] Optionally, in response to a triggering operation on the trial prompt information, obtaining the target human body model includes:

[0075] In response to a triggering operation on the trial prompt information, performing image acquisition to obtain at least one first image and at least one second image;

[0076] Sending the at least one first image and the at least one second image to a server;

[0077] Obtain the target human body model sent by the server.

[0078] Optionally, generating the three-dimensional human body image based on the object image of the target object and the target human body model includes:

[0079] Displaying selection prompt information of at least one item corresponding to the target object;

[0080] In response to the target user's item selection operation, determining a target item;

[0081] A fused image of the target item image and the three-dimensional human body image is displayed.

[0082] The embodiment of the present application generates a facial geometry model and a facial texture map based on at least one first image including the facial area of ​​the target user, generates a human body geometry model based on at least one second image including the human body area of ​​the target user, fuses the facial geometry model into the human body geometry model to generate a target human body geometry model, fuses the facial texture map into the human body texture map to generate a target texture map, obtains a target human body model based on the target texture map and the target human body geometry model, and the target human body model can be used to render and generate a three-dimensional human body image of the target user. The embodiment of the present application generates a three-dimensional human body image by combining images including facial areas or human body areas, and the facial areas and human body areas are generated separately and then fused, so that the user's facial image and the user's body shape system can be effectively restored, thereby improving the authenticity and accuracy of the three-dimensional human body image, thereby improving the display effect of the three-dimensional human body image.

[0083] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0085] FIG1 shows a schematic structural diagram of an embodiment of an information processing system provided by the present application;

[0086] FIG2 shows a flow chart of an embodiment of an image processing method provided by the present application;

[0087] FIG3 shows a flow chart of an embodiment of a display method provided by the present application;

[0088] FIG4 shows a schematic diagram of scene interaction in an actual application of an embodiment of the present application;

[0089] Figures 5a to 5d are schematic diagrams of models in a model generation process in a practical application of an embodiment of the present application;

[0090] FIG6 shows a schematic structural diagram of an image processing device according to an embodiment of the present application;

[0091] FIG7 shows a schematic structural diagram of an embodiment of a display device provided by the present application;

[0092] FIG8 shows a schematic structural diagram of an embodiment of a computing device provided by the present application. DETAILED DESCRIPTION

[0093] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0094] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0095] The technical solutions of the embodiments of the present application can be applied to application scenarios of human body data processing. Users can record their human body data online or obtain it through intelligent detection, and the human body data can be displayed to users for easy viewing. For example, in online shopping scenarios, size information will be provided for some wearable objects, such as clothing products. Users can view the human body data recorded by the online shopping platform, or obtain human body data by detecting the user's photos through the intelligent detection service provided by the online shopping platform, and select appropriate clothing products by comparing them with the size information of the clothing products. Currently, in order to improve the display effect, three-dimensional human body images can also be displayed. However, such three-dimensional human body images are all pre-configured and have no relevance to the user. The three-dimensional human body images displayed for different users are all the same, so the visual display effect is poor.

[0096] In order to improve the visual effect of three-dimensional human body images, the inventors have proposed the technical solution of the present application after a series of studies. In an embodiment of the present application, a facial geometry model and a facial texture map can be generated based on at least one first image including the facial area of ​​the target user, and a human body geometry model can be generated based on at least one second image including the human body area of ​​the target user. The facial geometry model is fused into the human body geometry model to generate a target human body geometry model, and the facial texture map is fused into the human body texture map to generate a target texture map. Based on the target texture map and the target human body geometry model, a target human body model is obtained. The target human body model can be used to render and generate a three-dimensional human body image of the target user. The embodiment of the present application generates a three-dimensional human body image by combining images including a facial area or a human body area, and the facial area and the human body area are generated separately and then fused, so that the user's facial image and the user's body shape system can be effectively restored, thereby improving the authenticity and accuracy of the three-dimensional human body image, thereby improving the display effect of the three-dimensional human body image.

[0097] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0098] The technical solution of the embodiment of the present application can be applied to the processing system shown in Figure 1. In actual applications, the processing system may include a user end 101 and a server end 102.

[0099] The client 101 and the server 102 may be connected via a network. The network provides a medium for a communication link between the client 101 and the server 102. The network may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0100] The user terminal 101 may be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5, version 5) application, a light application (also known as a mini-program, a lightweight application), or a cloud application. The user terminal 101 may be deployed in an electronic device and may rely on the device to run or on certain apps in the device to run. The electronic device may, for example, have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, tablet computer, personal computer, or other client terminal. For ease of understanding, FIG1 mainly uses a device image to represent the user terminal. Various other types of applications may also be configured in the electronic device, such as search applications, instant messaging applications, and the like.

[0101] The server 102 may include one or more servers that provide various services. For example, it may be implemented as a distributed server cluster consisting of multiple servers, or as a single server. In addition, it may be a server for a distributed system, or a server combined with a blockchain. It may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, or it may be an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0102] The user can interact with the server 102 through the user terminal 101 to receive or send messages, etc. In the application scenario of the embodiment of the present application, for example, the server can generate a target human body model, and the user terminal can display to the user a three-dimensional human body image rendered based on the target human body model.

[0103] For example, in an embodiment of the present application, the user terminal 101 can obtain at least one first image including the face area of ​​the target user and at least one second image including the body area of ​​the target user and send them to the server terminal 102. The server terminal 102 generates a human body geometry model based on the at least one first image and the at least one second image, fuses the face geometry model into the body geometry model to generate a target human body geometry model, fuses the face texture map into the body texture map to generate a target texture map, generates a target human body model based on the target texture map and the target human body geometry model, and sends it to the user terminal 101. The user terminal 101 renders a three-dimensional human body image based on the target human body model and displays it to the user.

[0104] It should be noted that the display method provided in the embodiment of the present application is generally executed by the user end, and the image processing method is generally executed by the server end. However, in other embodiments of the present application, the user end may have similar functions to the server end, and thus may also execute the image processing method provided in the embodiment of the present application.

[0105] It should be noted that the technical solution of the embodiment of the present application is applicable to a network virtual environment. The users described generally refer to "virtual users". Real users can register user accounts on the server through registration to obtain user identities in the network environment.

[0106] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0107] The implementation details of the technical solution of the embodiment of the present application are described in detail below.

[0108] FIG2 is a flowchart of an embodiment of an image processing method provided by the present application. The technical solution of this embodiment can be executed by a server. The method may include the following steps:

[0109] 201: Generate a face geometry model and a face texture map based on at least one first image including a face area of ​​a target user.

[0110] Among them, in order to further improve the visual display effect and user perception, optionally, generating a facial geometric model and a facial texture map based on at least one first image can also include: cartoonizing at least one first image to generate at least one cartoon facial image; generating a facial geometric model and a facial texture map based on at least one cartoon facial image.

[0111] A cartoonization processing model can be used to perform cartoonization processing on at least one first image to generate at least one cartoon face image. The cartoonization processing model can be pre-trained using training data, where the training data may include sample images as input data and cartoonized images corresponding to the sample images as training labels. The cartoonization processing model can be implemented using any machine learning model, which is not limited in this application.

[0112] Among them, a facial geometric model and a facial texture map can be generated based on the at least one first image through a three-dimensional reconstruction method, and the specific implementation method will be described in detail in the corresponding embodiments below.

[0113] The at least one image may include images of the target user's face at different angles, etc., so as to improve the accuracy of the facial geometry model and the facial texture map.

[0114] 202: Generate a human body geometric model based on at least one second image including a human body region of the target user.

[0115] Optionally, the at least one first image and the at least one second image may be provided by a user. Therefore, the method may further include:

[0116] At least one first image including a face area and at least one second image including a body area provided by a user are acquired.

[0117] Optionally, the user may extract the at least one first image and the at least one second image through a user terminal.

[0118] The second image and the first image may be the same image. A user may capture an image of a target user to obtain at least one human body image, and send the at least one human body image to a server. The server then identifies a facial region and a human body region from the at least one human body image, and uses the at least one human body image including the facial region as the first image and the at least one human body image including the human body region as the second image.

[0119] Optionally, the second image and the first image may also be different images. The user end may capture the front face area of ​​the target user from at least one angle to obtain at least one first image; and capture the body area of ​​the target user from at least one angle to obtain at least one second image; and send the at least one first image and the at least one second image to the server end.

[0120] In addition, the at least one second image and the at least one first image may also be uploaded locally by the user to the user terminal, and then sent from the user terminal to the server terminal.

[0121] The at least one second image and the at least one first image may be two-dimensional images.

[0122] Among them, the human body geometric model can be generated through three-dimensional reconstruction.

[0123] 203: Fusing the face geometry model into the body geometry model to generate a target body geometry model.

[0124] The face geometric model may be used to replace the face area of ​​the body geometric model to generate a target body combined model.

[0125] 204: Fusing the face texture map into the body texture map to generate a target texture map.

[0126] The target texture map may be generated by combining the face texture map with the body texture map. If the body texture map includes a face area, the face texture map may be replaced with the face area of ​​the body texture map to obtain the target texture map.

[0127] The human body texture map may be selected and determined from at least one preset human body texture map.

[0128] 205: Obtain a target human body model based on the target texture map and the target human body geometry model.

[0129] The target body model is obtained by attaching the target texture map to the target body geometry model. The target body model is used to render and generate a 3D body image of the target user.

[0130] The three-dimensional human body image may be generated by rendering a target human body model according to first camera parameters.

[0131] The first camera parameters may include a first camera position and a first camera height. For example, the first camera position may be a horizontal position relative to the target human model, such as being directly in front of, directly behind, directly to the left, directly to the right, or diagonally behind the target human model. The first camera height may be a height relative to a certain part of the target human model to achieve the effects of shooting from above, horizontally, or downward.

[0132] In this embodiment, a facial geometry model and a facial texture map are generated based on at least one first image including a facial area of ​​the target user, and a human body geometry model is generated based on at least one second image including a human body area of ​​the target user. The facial geometry model is fused into the human body geometry model to generate a target human body geometry model; the facial texture map is fused into the human body texture map to generate a target texture map, and a target human body model is obtained based on the target texture map and the target human body geometry model. The target human body model is used to render and generate a three-dimensional human body image of the target user. The embodiment of the present application generates a three-dimensional human body image by combining images including a facial area or a human body area, and the facial area and the human body area are generated separately and then fused, so that the user's facial image and the user's body shape system can be effectively restored, thereby improving the authenticity and accuracy of the three-dimensional human body image, thereby improving the display effect of the three-dimensional human body image.

[0133] In some embodiments, generating a facial geometric model and a facial texture map based on at least one first image may include:

[0134] Performing three-dimensional reconstruction on the at least one first image to obtain a face geometric model;

[0135] Performing texture sampling based on the at least one first image and the face geometric model to obtain a first texture map corresponding to the facial area;

[0136] The first texture map is fused with the second texture map corresponding to the non-facial area to obtain a face texture map.

[0137] Optionally, when cartooning at least one first image, specifically, three-dimensional reconstruction can be performed on the at least one cartoonized image to obtain a facial geometric model; and texture sampling can be performed based on the at least one cartoonized image and the facial geometric model to obtain a first texture map corresponding to the facial area; thereby making the final restored face a cartoonized image to improve the visual experience.

[0138] Among them, texture sampling can be achieved by projecting the facial geometric model into at least one first image respectively, and the three-dimensional vertex coordinates in the facial geometric model can obtain corresponding two-dimensional plane coordinates through projection. Based on the two-dimensional plane coordinates, pixel sampling can be performed in the at least one first image, and the pixel colors at the two-dimensional plane coordinates corresponding to the three-dimensional vertex coordinates in the at least one first image can be fused, such as weighted processing, etc., which can be used as a texture map corresponding to the three-dimensional vertex coordinates, and finally the first texture map corresponding to the facial geometric model is obtained.

[0139] There are multiple implementation methods for determining the second texture map. As an optional implementation method, performing three-dimensional reconstruction on at least one first image to obtain a face geometric model may include:

[0140] The at least one first image is three-dimensionally reconstructed using a parameterized model to obtain a face geometric model and a second texture map.

[0141] The parameterized model can, for example, adopt 3DMM (3D Morphable models, three-dimensional deformable face models), BFM (Basel Face Model, a three-dimensional face model), and FLAME (a three-dimensional face model). The parameterized model can be based on at least one first input image, and a certain number of face images in the face database can be weighted linearly added by orthogonal basis to obtain the corresponding face geometric model and the second texture map.

[0142] The second texture map obtained by using the parameterized model is obtained from a face image in a face database and may have a low resolution. Therefore, it can be used as a texture map of a non-face area to complete the texture map of the face area to obtain a face texture map.

[0143] As another optional implementation, the second texture map may be pre-configured and obtained. Optionally, the method may further include:

[0144] A second texture map corresponding to the non-face area is determined from at least one preset non-face texture map template.

[0145] The at least one preset non-facial texture map template may be one or more, and the multiple preset non-facial texture map templates may correspond to different facial types, such as skin color, shape, etc.

[0146] Determining a second texture map corresponding to a non-facial area from at least one preset non-facial texture map template can be done by inputting at least one first image into a matching model to determine the corresponding target facial type, thereby using the preset non-facial texture map template corresponding to the target facial type as the second texture map.

[0147] The matching model can be obtained by training using sample images and facial types corresponding to the sample images as training samples.

[0148] The fusion of the first texture map and the second texture map may be performed by extracting a texture map of the facial area from the first texture map and splicing it with a texture map of the non-facial area extracted from the second texture map to obtain a facial texture map.

[0149] In some embodiments, the fusion of the first texture map with the second texture map corresponding to the non-facial area can be achieved using image mask technology. In this embodiment, a facial mask can be set, with the area within the mask representing the frontal face area, i.e., the facial area, and the area outside the mask representing the non-facial area, such as the sides of the face, ears, neck, and other parts. The texture map within the mask can be generated using the first texture map obtained based on at least one first image, and the texture map outside the mask can be generated using the second texture map, thereby obtaining a facial texture map.

[0150] In addition, when the first texture map corresponding to the facial area is fused with the second texture map corresponding to the non-facial area, a Gaussian smoothing algorithm can be used to smooth the color at the boundary between the facial area and the non-facial area to make the transition of the boundary area natural.

[0151] In some embodiments, facial texture maps can also be whitened. For example, a face detection algorithm such as face parsing can be used to detect the skin area in the facial texture map, and then, based on a pre-designed whitening color mapping table, the pixels in the skin area can be color-mapped to achieve a whitening effect. Of course, this application does not specifically limit the specific whitening algorithm.

[0152] In addition, other beautification processing can be performed on the facial texture map, which is not limited in this application.

[0153] In some embodiments, to further improve the visual effect, the target human body model may include a hairstyle model to make the target human body model more complete. The method may further include: determining a hairstyle geometry model and a hairstyle texture map corresponding to the target user;

[0154] Accordingly, fusing the face geometry model into the body geometry model to generate the target body geometry model may include fusing the hairstyle geometry model and the face geometry model into the body geometry model to generate the target body geometry model.

[0155] Accordingly, fusing the face texture map into the body texture map to generate the target texture map may include: fusing the hairstyle texture map and the face texture map into the body texture map to generate the target texture map.

[0156] Therefore, based on the target human body geometric model fused with the hairstyle geometric model and the target texture map fused with the hairstyle texture map, a target human body model including the hairstyle model can be generated.

[0157] The hairstyle geometric model and the hairstyle texture map may be pre-configured.

[0158] In addition, to further improve the visual effect, different hairstyle categories may be pre-configured with hairstyle geometric models and hairstyle texture maps. Therefore, in some embodiments, determining the hairstyle geometric model and hairstyle texture map corresponding to the target user may include:

[0159] Based on the at least one first image, a hairstyle category corresponding to the target user is identified; and a hairstyle texture map and a hairstyle geometric model corresponding to the hairstyle category are determined.

[0160] Identifying the hairstyle category corresponding to the target user based on the at least one first image may include: identifying the hairstyle category corresponding to the target user based on the at least one first image using a recognition model, wherein the recognition model is pre-trained based on sample images and their corresponding hairstyle categories.

[0161] In some embodiments, in order to further improve the visual effect, after obtaining the target human body model, the method may further include:

[0162] The skeletal animation corresponding to the target human body model is determined, wherein the target human body model is used to generate a dynamically changing three-dimensional human body image in combination with the skeletal animation rendering.

[0163] Among them, one or more skeletal animation templates can be provided, and any skeletal animation template can be randomly selected to bind the target human body model to the corresponding position of the corresponding bone point in the skeletal animation template. The target human body model can be driven according to the skeletal animation in the skeletal animation template, thereby rendering and generating a dynamically changing three-dimensional human body image to enhance the visual effect.

[0164] The human body texture map may be pre-configured and obtained. In some embodiments, the method may further include: selecting a human body texture map from at least one preset human body texture map template.

[0165] Optionally, when there are multiple preset human body texture map templates, one of the preset human body texture map templates may be randomly selected as the human body texture map.

[0166] Among them, a parametric model can also be used to perform three-dimensional reconstruction on at least one second image to obtain a human body geometric model, and other non-parametric models can also be used for three-dimensional reconstruction, which is not limited in this application.

[0167] FIG3 is a flowchart of an embodiment of a display method provided by the present application. The technical solution of this embodiment can be executed by a user terminal. The method may include the following steps:

[0168] 301: Displaying a three-dimensional human body image generated by rendering based on a target human body model.

[0169] The target human body model can be generated based on a target texture map and a target human body geometry model. The target human body geometry model is obtained by fusing a face geometry model into a human body geometry model; the target texture map is obtained by fusing a face texture map into a human body texture map.

[0170] The face geometry model and the face texture map are generated based on at least one first image including a face area of ​​the target user; and the body geometry model is generated based on at least one second image including a body area of ​​the target user.

[0171] The target human body model obtained by the user end may be generated and sent by the server end.

[0172] Therefore, optionally, the method may further include: acquiring a target human body model sent by the server; and generating a three-dimensional human body image based on rendering of the target human body model.

[0173] The specific method of generating the target human body model can be found in the embodiment shown in FIG2 , and will not be described in detail here.

[0174] In this embodiment, the user terminal displays a three-dimensional human body image generated based on the rendering of a target human body model. The target human body image is generated by the server terminal based on a target texture map and a target human body geometry model. The target human body geometry model is obtained by fusing a facial geometry model into a human body geometry model; the target texture map is obtained by fusing a facial texture map into a human body texture map; the facial geometry model and the facial texture map are generated based on at least one first image including the facial region of the target user; and the human body geometry model is generated based on at least one second image including the human body region of the target user. The embodiment of the present application generates a three-dimensional human body image by combining images including facial regions or human body regions, and the facial regions and human body regions are generated separately and then fused, so that the user's facial image and the user's body shape system can be effectively restored, thereby improving the authenticity and accuracy of the three-dimensional human body image, thereby improving the display effect of the three-dimensional human body image.

[0175] As an optional method, the method may further include:

[0176] Capturing a frontal face area of ​​a target user from at least one angle to obtain at least one first image;

[0177] capturing a human body region of a target user from at least one angle to obtain at least one second image;

[0178] At least one first image and at least one second image are sent to a server.

[0179] Thus, the server can generate a target human body model based on the at least one first image and the at least one second image.

[0180] Optionally, a capture prompt may be displayed first, which may be used to prompt the user on a capture method. Based on the user's capture operation, the frontal face area of ​​the target user may be captured from at least one angle to obtain at least one first image; and the body area of ​​the target user may be captured from at least one angle to obtain at least one second image.

[0181] The server can generate a target human body model based on at least one first image and at least one second image. The specific generation method can be found in the corresponding embodiments above and will not be repeated here.

[0182] In some embodiments, as another optional manner, the method may further include:

[0183] Capturing an image of a target user from at least one angle to obtain at least one human body image;

[0184] identifying a face region and a body region from at least one human body image;

[0185] using at least one human body image including a face region as a first image;

[0186] At least one human body image including a human body region is used as the second image.

[0187] In some embodiments, in order to enrich the forms of interaction with the user, the method may further include:

[0188] detecting a first interactive operation on the three-dimensional human body image;

[0189] The three-dimensional human body image is rotated and the rotated three-dimensional human body image is displayed.

[0190] Among them, rotating the three-dimensional human body image and displaying the rotated three-dimensional human body image may include: taking the vertical direction as the rotation axis, following the change of the contact position, rotating the three-dimensional human body image in a preset rotation direction, and displaying the rotated three-dimensional human body image after the first interactive operation ends.

[0191] The first interactive operation may be, for example, a left-right swipe operation on the 3D human image. Rotating the 3D human image and displaying the rotated 3D human image may involve rotating the 3D human image in a predetermined direction with the vertical axis as the rotation axis, following the change in the touch point position, and displaying the rotated 3D human image after the first interactive operation ends.

[0192] Specifically, by rotating the three-dimensional human body image in a preset direction with the vertical direction as the rotation axis, a plurality of camera parameters corresponding to the preset direction can be determined, and a plurality of corresponding three-dimensional human body images can be generated.

[0193] In addition, after the rotated three-dimensional human body image is displayed, the original three-dimensional human body image may be restored if no interactive operation is detected within a predetermined time.

[0194] In some embodiments, the method may further include:

[0195] detecting a second interactive operation on the three-dimensional human body image;

[0196] The three-dimensional human body image is switched and displayed as a partial human body image, and the corresponding dynamically changing image is displayed during the switching process.

[0197] The dynamically changing image corresponding to the partial human body image may be displayed first, after which the dynamic changing image is displayed. The dynamic changing image and the partial human body image are displayed consecutively, so that the three-dimensional human body image, the dynamic changing image, and the partial human body image are smoothly connected.

[0198] The partial human body image may be determined according to the interaction position of the second interaction operation, and may be an image of a certain area where the interaction position is located, or may be an image of a characteristic part corresponding to the characteristic part corresponding to the interaction position.

[0199] Displaying the corresponding dynamically changing image during the switching process may include: displaying a dynamically changing image formed by target images corresponding to the plurality of camera parameters during the switching process. The target images corresponding to the plurality of camera parameters may be combined in an arrangement order corresponding to the plurality of camera parameters to generate the dynamically changing image, which is also a video generated by the plurality of target images.

[0200] This embodiment can realize the switching display of the overall image and the local image, and connect them through dynamically changing images, thereby improving the visual effect, enriching the interaction form, and realizing effective interaction with the user.

[0201] In some embodiments, the method may further include:

[0202] Acquire human body data of a target user identified in at least one second image;

[0203] The human body data is displayed at the corresponding characteristic parts in the three-dimensional human body image.

[0204] The server may identify the body data of the target user from at least one second image and send the data to the user.

[0205] Corresponding feature labels may also be displayed at multiple feature locations in the three-dimensional human body image.

[0206] Correspondingly, detecting the second interactive operation for the three-dimensional human body image may be detecting a trigger operation for any feature tag, and switching the three-dimensional human body image to a partial human body image may be switching the three-dimensional human body image to a partial human body image of the feature part corresponding to the feature tag.

[0207] Among them, the feature tag can display the feature data of the corresponding feature part, which can be implemented in the form of a control for user interaction.

[0208] In some embodiments, the method may further include:

[0209] Determining at least one object that matches the target user;

[0210] Display object prompt information of at least one object;

[0211] In response to a triggering operation of the target user on the object prompt information, determining a corresponding target object;

[0212] A fused image of the object image and the three-dimensional human body image of the target object is displayed.

[0213] The object can be a single item of a product. A product is often a combination of multiple items. In e-commerce scenarios, a single item can be represented as a stock keeping unit (SKU), and a product can be represented as a standard product unit (SPU). The object prompt information can include trial prompt information for each object. Furthermore, in response to a triggering operation for any trial prompt information, an object image corresponding to the target object can be determined; the object image can be fused with a three-dimensional human body image to generate a fused image, which can be displayed.

[0214] In addition, the object prompt information may further include processing prompt information, and corresponding processing may be performed on the target object in response to a triggering operation for any processing prompt information.

[0215] The processing prompt information may include a processing control corresponding to at least one processing type. In response to a triggering operation for any processing prompt information, performing corresponding processing on the target object may include:

[0216] In response to a triggering operation of a processing control for any processing type, the target object is processed accordingly according to the processing type.

[0217] The processing control may include an add-to-cart control. Accordingly, in response to a triggering operation on the add-to-cart control, the target object may be added to the shopping cart.

[0218] The processing control may also include a transaction control. Accordingly, in response to a trigger operation on the transaction control, an order request may be generated based on the target object.

[0219] This embodiment can be applied to object exchange scenarios. Users can trigger trial prompt information for different objects, view images of different objects fused with three-dimensional human images, feel the effects of different objects being tried on the user's body, and make purchase or exchange operations for the desired objects.

[0220] In some embodiments, the method may further include:

[0221] Display trial prompt information on the target object's object details page;

[0222] In response to a triggering operation on the trial prompt information, obtaining a target human body model;

[0223] A three-dimensional human body image is generated based on the object image of the target object and the target human body model.

[0224] The target object may be a target product, which includes multiple items. The target product may include attribute parameters such as size, style, and performance parameters. Multiple items may be obtained by combining different attribute parameters of the target product.

[0225] Accordingly, generating a three-dimensional human body image based on the object image of the target object and the target human body model may include generating a three-dimensional human body image based on a single item image of the target single item and the target human body model.

[0226] Among them, the target item can be obtained based on the human body data matching of the target user identified from at least one second image. For example, the target product is a style of jeans. The sports pants are divided into three sizes: S, M, and L. The S size is suitable for people with a waist circumference of 66 to 68 cm, the M size is suitable for people with a waist circumference of 68 to 70 cm, and the L size is suitable for people with a waist circumference of 70 to 72 cm. If the waist circumference of the target user is identified as 69 cm, the matched target item is the M size sports pants item.

[0227] In addition, as another optional method, generating the three-dimensional human body image based on the object image of the target object and the target human body model may include: displaying selection prompt information of at least one item corresponding to the target object; determining the target item in response to the item selection operation of the target user; and displaying a fused image of the item image of the target item and the three-dimensional human body image.

[0228] That is, the target item can also be selected and determined by the user.

[0229] This embodiment can be applied to object exchange scenarios. Users can trigger trial prompt information to view the three-dimensional human image generated by the target object and the user's human body data, thereby improving the recommendation effect of the target object and further improving the conversion rate of the target object.

[0230] In some embodiments, in response to a trigger operation for the trial prompt information, obtaining the target human body model may include: in response to a trigger operation for the trial prompt information, performing image acquisition to obtain at least one first image and at least one second image; sending the at least one first image and the at least one second image to a server; and obtaining the target human body model sent by the server;

[0231] That is, the triggering operation of the trial prompt information can trigger the image acquisition operation. The trial prompt information may include acquisition prompt information to prompt the user on the acquisition method, so that image acquisition can be performed according to the user's acquisition operation to obtain a set of at least one first image and at least one second image, etc.

[0232] The server can generate a target human body model based on at least one first image and at least one second image. The specific generation method can be found in the corresponding embodiments above and will not be repeated here.

[0233] For ease of understanding, refer to the scene interaction schematic diagram shown in Figure 4. The technical solution of the embodiment of the present application is introduced below in combination with the scene interaction schematic diagram shown in Figure 4.

[0234] The user terminal 401 can capture images of the target user, capture the front face area of ​​the target user from at least one angle to obtain at least one first image, and capture the body area of ​​the target user from at least one angle to obtain at least one second image, and send the at least one first image and the at least one second image to the server terminal 402.

[0235] The server 402 may generate a human body geometric model 500 as shown in FIG. 5 a based on the at least one second image, generate a facial geometric model 501 as shown in FIG. 5 a and a facial texture map 502 as shown in FIG. 5 b based on the at least one first image, and determine a hairstyle geometric model 503 as shown in FIG. 5 a and a hairstyle texture map 504 as shown in FIG. 5 b corresponding to the target user.

[0236] The face geometric model 501 replaces the face area of ​​the body geometric model 500 , and the hairstyle geometric model 502 is added to the body geometric model to generate a target body geometric model 505 .

[0237] Server 402 can randomly select a preset human body texture template from multiple preset human body texture templates as human body texture map 506. Hair style texture map 504 and face texture map 502 are merged into human body texture map 506 to generate target texture map 507. The target texture map and the target human body geometry model constitute the target human body model, which can be rendered to generate a three-dimensional human body image as shown in Figure 5c.

[0238] After generating the target human body model, the server 402 can also randomly select a skeletal animation template as shown in Figure 5d, bind the target human body model to the corresponding positions of the corresponding bone points in the skeletal animation template, and then drive the target human body model according to the skeletal animation in the skeletal animation template as shown in Figure 5d, generate a dynamic target human body model and send it to the user terminal 401. The user terminal 401 renders and generates a dynamically changing three-dimensional human body image based on the dynamic target human body model.

[0239] FIG6 is a schematic diagram of the structure of an embodiment of an image processing device provided by an embodiment of the present application, wherein the method and device include:

[0240] A first generating module 601 is configured to generate a face geometry model and a face texture map based on at least one first image including a face region of a target user;

[0241] A second generating module 602 is configured to generate a human body geometric model based on at least one second image including a human body region of a target user;

[0242] The third generation module 603 is used to fuse the face geometry model into the body geometry model to generate a target body geometry model;

[0243] The fourth generating module 604 is used to fuse the face texture map into the body texture map to generate a target texture map;

[0244] The fifth generating module 605 is configured to obtain a target human body model based on the target texture map and the target human body geometric model.

[0245] The target human body model is used to render and generate a three-dimensional human body image of the target user.

[0246] The human body texture map may be pre-configured and may be selected from at least one preset human body texture map template.

[0247] Optionally, when there are multiple preset human body texture map templates, one of the preset human body texture map templates may be randomly selected as the human body texture map.

[0248] In some embodiments, the first generation module generates a facial geometric model and a facial texture map based on at least one first image, which may include: performing three-dimensional reconstruction on at least one first image to obtain a facial geometric model; performing texture sampling based on at least one first image and the facial geometric model to obtain a first texture map corresponding to the facial area; and fusing the first texture map with the second texture map corresponding to the non-facial area to obtain a facial texture map.

[0249] There are multiple implementation methods for determining the second texture map. As an optional implementation method, performing three-dimensional reconstruction on at least one first image to obtain a face geometric model may include:

[0250] The at least one first image is three-dimensionally reconstructed using a parameterized model to obtain a face geometric model and a second texture map.

[0251] As another optional implementation, the second texture map may be pre-configured and obtained. Optionally, the method may further include: determining the second texture map corresponding to the non-facial area from at least one preset non-facial texture map template.

[0252] In some embodiments, the device may further include a beautification processing module for whitening the facial texture map. For example, a face detection algorithm such as face parsing may be used to detect the skin region in the facial texture map, and a pre-designed whitening color mapping table may be used to perform a color mapping transformation on the pixels in the skin region to achieve a whitening effect. Of course, this application does not specifically limit the specific whitening algorithm.

[0253] In addition, other beautification processing can be performed on the facial texture map, which is not limited in this application.

[0254] In some embodiments, in order to further improve the visual effect, the target human body model may include a hairstyle model to make the target human body model more vivid. The device may also include a hairstyle recognition module for determining the hairstyle geometry model and hairstyle texture map corresponding to the target user.

[0255] Accordingly, the third generation module fuses the face geometry model into the body geometry model, and generating the target body geometry model may include: fusing the hairstyle geometry model and the face geometry model into the body geometry model to generate the target body geometry model.

[0256] Accordingly, the fourth generating module fuses the face texture map into the body texture map to generate the target texture map, which may include: fusing the hairstyle texture map and the face texture map into the body texture map to generate the target texture map.

[0257] Therefore, the fifth generating module can generate a target human body model including a hairstyle model based on the target human body geometric model integrated with the hairstyle geometric model and the target texture map integrated with the hairstyle texture map.

[0258] The hairstyle geometric model and the hairstyle texture map may be pre-configured.

[0259] In some embodiments, in order to further improve the visual effect, after obtaining the target human body model, the device may also include an animation generation module for determining the skeletal animation corresponding to the target human body model, wherein the target human body model is used to generate a dynamically changing three-dimensional human body image in combination with the skeletal animation rendering.

[0260] The processing device shown in FIG6 can execute the image processing method described in the embodiment shown in FIG2. The implementation principle and technical effects thereof are not described in detail here. The specific manner in which each module and unit in the processing device in the above embodiment performs operations has been described in detail in the embodiment of the method and will not be elaborated on here.

[0261] FIG7 is a schematic structural diagram of an embodiment of a display device provided by an embodiment of the present application, wherein the method and device include:

[0262] The display module 701 is configured to display a three-dimensional human body image generated by rendering based on a target human body model.

[0263] Among them, the target human body model is generated based on the target texture map and the target human body geometry model. The target human body geometry model is obtained by fusing the face geometry model into the human body geometry model; the target texture map is obtained by fusing the face texture map into the human body texture map; the face geometry model and the face texture map are generated based on at least one first image including the face area of ​​the target user; the human body geometry model is generated based on at least one second image including the human body area of ​​the target user.

[0264] In some embodiments, in order to enrich the forms of interaction with the user, the device may further include a first interaction module for detecting a first interaction operation on the three-dimensional human image; rotating the three-dimensional human image and displaying the rotated three-dimensional human image.

[0265] Among them, rotating the three-dimensional human body image and displaying the rotated three-dimensional human body image may include: taking the vertical direction as the rotation axis, following the change of the contact position, rotating the three-dimensional human body image in a preset rotation direction, and displaying the rotated three-dimensional human body image after the first interactive operation ends.

[0266] In addition, after the rotated three-dimensional human body image is displayed, the original three-dimensional human body image may be restored if no interactive operation is detected within a predetermined time.

[0267] In some embodiments, the device may further include a second interaction module configured to detect a second interaction operation on the three-dimensional human body image; switch the three-dimensional human body image to a partial human body image, and display a corresponding dynamically changing image during the switching process.

[0268] The dynamically changing image corresponding to the partial human body image may be displayed first, after which the dynamic changing image is displayed. The dynamic changing image and the partial human body image are displayed consecutively, so that the three-dimensional human body image, the dynamic changing image, and the partial human body image are smoothly connected.

[0269] The partial human body image may be determined according to the interaction position of the second interaction operation, and may be an image of a certain area where the interaction position is located, or may be an image of a characteristic part corresponding to the characteristic part corresponding to the interaction position.

[0270] Displaying the corresponding dynamically changing image during the switching process may include: displaying a dynamically changing image formed by target images corresponding to the plurality of camera parameters during the switching process. The target images corresponding to the plurality of camera parameters may be combined in an arrangement order corresponding to the plurality of camera parameters to generate the dynamically changing image, which is also a video generated by the plurality of target images.

[0271] In some embodiments, the device may further include a second display module, configured to obtain body data for identifying a target user in at least one second image; and display the body data at corresponding feature locations in the three-dimensional body image.

[0272] The server may identify the body data of the target user from at least one second image and send the data to the user.

[0273] Corresponding feature labels may also be displayed at multiple feature locations in the three-dimensional human body image.

[0274] Correspondingly, detecting the second interactive operation for the three-dimensional human body image may be detecting a trigger operation for any feature tag, and switching the three-dimensional human body image to a partial human body image may be switching the three-dimensional human body image to a partial human body image of the feature part corresponding to the feature tag.

[0275] Among them, the feature tag can display the feature data of the corresponding feature part, which can be implemented in the form of a control for user interaction.

[0276] In some embodiments, the device may also include a third display module for determining at least one object matching the target user; displaying object prompt information of at least one object; determining the corresponding target object in response to the target user's triggering operation on the object prompt information; and displaying a fused image of the object image of the target object and the three-dimensional human body image.

[0277] The object may be a single item of a product. The object prompt information may include trial prompt information. Furthermore, in response to a triggering operation on any trial prompt information, an object image corresponding to the target object may be determined; the object image may be fused with the three-dimensional human body image to generate a fused image, and the fused image may be displayed.

[0278] For example, the object prompt information may further include processing prompt information, and corresponding processing may be performed on the target object in response to a triggering operation for any processing prompt information.

[0279] The processing prompt information may include a processing control corresponding to at least one processing type. In response to a triggering operation for any processing prompt information, performing corresponding processing on the target object may include:

[0280] In response to a triggering operation of a processing control for any processing type, the target object is processed accordingly according to the processing type.

[0281] The processing control may include an add-to-cart control. Accordingly, in response to a triggering operation on the add-to-cart control, the target object may be added to the shopping cart.

[0282] The processing control may also include a transaction control. Accordingly, in response to a trigger operation on the transaction control, an order request may be generated based on the target object.

[0283] In some embodiments, the device may further include a fourth display module for displaying prompt information in the object details page; obtaining a target human body model in response to a trigger operation for the prompt information; and generating a three-dimensional human body image based on the object image of the target object and the target human body model.

[0284] The display device shown in FIG7 can execute the display method described in the embodiment shown in FIG3, and its implementation principle and technical effects are not described in detail here. The specific manner in which each module and unit of the display device in the above embodiment performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0285] The embodiment of the present application further provides a computing device, as shown in FIG8 , which may include a storage component and a processing component;

[0286] The storage component stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component to implement the image processing method described in the embodiment shown in FIG2 or the display method described in the embodiment shown in FIG3.

[0287] Of course, the computing device may also include other components, such as input / output interfaces, communication components, etc. When the computing device implements the information display method described in the embodiment shown in FIG3 , the computing device may also include a display component, etc.

[0288] The input / output interface provides an interface between the processing component and peripheral interface modules, which may be output devices, input devices, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices.

[0289] The processing component 802 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0290] The storage component 801 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0291] The display component may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a direct retinal display or a similar laser scanning display.

[0292] It should be noted that when the above-mentioned computing device implements the display method described in the embodiment of Figure 3, it can be specifically implemented as an electronic device. The electronic device can refer to a device used by the user, which has the computing, Internet access, communication and other functions required by the user, such as a mobile phone, tablet computer, personal computer, wearable device, etc.

[0293] When implementing the image processing method described in the embodiment shown in FIG2 , the computing device can be a physical device or an elastic computing host provided by a cloud computing platform. It can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device.

[0294] The present application also provides a computer-readable storage medium storing a computer program. When executed by a computer, the computer program can implement the image processing method described in the embodiment shown in FIG2 or the display method described in the embodiment shown in FIG3. The computer-readable medium can be included in the electronic device described in the above embodiments, or it can exist independently and not be incorporated into the electronic device.

[0295] An embodiment of the present application also provides a computer program product, which includes a computer program carried on a computer-readable storage medium. When the computer program is executed by a computer, it can implement the image processing method described in the embodiment shown in Figure 2 or the display method described in the embodiment shown in Figure 3.

[0296] In such an embodiment, the computer program may be downloaded and installed from a network, and / or installed from a removable medium. When the computer program is executed by a processor, various functions defined in the system of the present application are performed.

[0297] In the above corresponding embodiments, the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component.

[0298] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0299] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0300] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0301] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An image processing method, It is characterized in that include: Generate a face geometry model and a face texture map based on at least one first image including a face region of a target user; generating a human body geometric model based on at least one second image including a human body region of the target user; Fusion of the face geometry model into the body geometry model to generate a target body geometry model; Merging the face texture map into the body texture map to generate a target texture map; Based on the target texture map and the target human body geometric model, obtaining a target human body model; The target human body model is used to render and generate a three-dimensional human body image of the target user.

2. The method according to claim 1, It is characterized in that The generating of the face geometry model and the face texture map based on the at least one first image comprises: Performing three-dimensional reconstruction on the at least one first image to obtain a face geometric model; Based on the at least one first image and the face geometric model, texture sampling is performed to obtain a first texture map corresponding to the facial area; The first texture map is merged with the second texture map corresponding to the non-facial area to obtain a face texture map.

3. The method according to claim 2, It is characterized in that The three-dimensional reconstruction of the at least one first image to obtain a face geometric model comprises: The at least one first image is three-dimensionally reconstructed using a parameterized model to obtain a face geometry model and the second texture map.

4. The method according to claim 1, It is characterized in that The generating of the face geometry model and the face texture map based on the at least one first image comprises: Performing cartoon processing on the at least one first image to generate at least one cartoon face image; A face geometry model and a face texture map are generated based on the at least one cartoon face image.

5. The method according to claim 1, It is characterized in that Also includes: Based on the at least one first image, identifying a hairstyle category corresponding to the target user; Determine a hairstyle texture map and a hairstyle geometric model corresponding to the hairstyle category; The step of fusing the face geometry model into the body geometry model to generate a target body geometry model comprises: The hairstyle geometric model and the face geometric model are integrated into the human body geometric model to generate a target human body geometric model; The step of fusing the face texture map into the body texture map to generate a target texture map comprises: The hairstyle texture map and the face texture map are merged into the body texture map to generate a target texture map.

6. The method according to claim 1, It is characterized in that After obtaining the target human body model, the method further includes: The skeletal animation corresponding to the target human body model is determined; the target human body model is used to generate a dynamically changing three-dimensional human body image in combination with the skeletal animation rendering.

7. The method according to claim 1, It is characterized in that Also includes: The human body texture map is selected from at least one preset human body texture map template.

8. A display method, It is characterized in that include: Displaying a three-dimensional human body image generated based on the target human body model rendering; Among them, the target human body model is generated based on a target texture map and a target human body geometry model, the target human body geometry model is obtained by fusing a face geometry model into a human body geometry model; the target texture map is obtained by fusing a face texture map into a human body texture map; the face geometry model and the face texture map are generated based on at least one first image including a face area of ​​a target user; the human body geometry model is generated based on at least one second image including a human body area of ​​the target user.

9. The method according to claim 8, It is characterized in that Also includes: Obtain the target human body model sent by the server; The three-dimensional human body image is generated based on the target human body model rendering.

10. The method according to claim 9, It is characterized in that Also includes: Capturing a front face area of ​​a target user from at least one angle to obtain at least one first image; Capturing a human body region of the target user from at least one angle to obtain at least one second image; The at least one first image and the at least one second image are sent to a server.

11. The method according to claim 8, It is characterized in that Also includes: Determining at least one object matching the target user; displaying object prompt information of the at least one object; In response to a triggering operation of the target user on the object prompt information, determining a corresponding target object; A fused image of the object image of the target object and the three-dimensional human body image is displayed.

12. The method according to claim 8, It is characterized in that Also includes: Display trial prompt information in the object details page of the target object; In response to a triggering operation on the trial prompt information, acquiring the target human body model; The three-dimensional human body image is generated based on the object image of the target object and the target human body model.

13. A computing device, It is characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the image processing method as described in any one of claims 1 to 7 or the display method as described in any one of claims 8 to 12.

14. A computer storage medium, It is characterized in that A computer program is stored, and when the computer executes the computer program, the image processing method according to any one of claims 1 to 7 or the display method according to any one of claims 8 to 12 is implemented.

Citation Information

Patent Citations

  • Method and system for creating 3D human body model based on user image

    CN107680167A

  • Three-dimensional human body parametric modeling method with high-fidelity facial features

    CN111127641A

  • Three-dimensional human body reconstruction method and device, equipment and storage medium

    CN112950769A

  • Three-dimensional human body reconstruction method and device, equipment and storage medium

    CN113012282A

  • Three-dimensional model generation method and device

    CN114758090A