Clothing texture map generation method and device, equipment and storage medium

Abstract

The invention provides a costume texture map generation method and device, equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical fields of computer vision, deep learning, large models and the like, and can be applied to scenes such as virtual reality and digital human. According to the specific implementation scheme, costume features are obtained based on a costume reference picture; obtaining texture features according to the coordinate mapping graph and the texture mask graph associated with the clothing reference graph; wherein the coordinate mapping graph comprises a coordinate corresponding to a texture map expanded by a costume model associated with the costume reference graph in the costume model; the texture mask graph comprises an image generated based on a transparent channel in a texture map expanded by the clothing model; and generating a clothing texture map based on the clothing features and the texture features.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to technical fields such as computer vision, deep learning, and large models, and can be applied to scenarios such as virtual reality and digital humans. Background Art

[0002] With the development of virtual reality and augmented reality technologies, digital characters such as digital humans are being used in more and more scenarios. For example, in social media and virtual interactive platforms, digital humans can provide an immersive user experience. High-quality 3D models and realistic textures are essential for the authenticity and interactivity of digital characters. Summary of the invention

[0003] The present invention provides a method, device, equipment and storage medium for generating clothing texture maps.

[0004] According to one aspect of the present disclosure, a method for generating a clothing texture map is provided, comprising:

[0005] Obtain clothing features based on clothing reference images;

[0006] The texture feature is obtained according to a coordinate mapping map and a texture mask map associated with the clothing reference image; wherein the coordinate mapping map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference image in the clothing model; and the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model;

[0007] A clothing texture map is generated based on the clothing feature and the texture feature.

[0008] According to another aspect of the present disclosure, a clothing texture map generation model training method is provided, comprising:

[0009] Obtain clothing features based on clothing reference images in training samples;

[0010] According to the coordinate mapping map and the texture mask map in the training sample and the input noise, a texture feature is obtained; wherein the coordinate mapping map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference image in the clothing model; the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model;

[0011] Based on the clothing features and the texture features, the clothing texture map generation model is optimized.

[0012] According to another aspect of the present disclosure, a clothing texture map generating device is provided, comprising:

[0013] A clothing feature acquisition module, used to obtain clothing features based on a clothing reference image;

[0014] A texture feature acquisition module, configured to obtain texture features according to a coordinate map and a texture mask map associated with the clothing reference image; wherein the coordinate map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference image in the clothing model; and the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model;

[0015] The clothing map generation module is used to generate a clothing texture map based on the clothing features and the texture features.

[0016] According to another aspect of the present disclosure, a clothing texture map generation model training device is provided, comprising:

[0017] A clothing feature acquisition module, used to obtain clothing features based on clothing reference images in training samples;

[0018] A texture feature acquisition module, configured to obtain texture features according to a coordinate map and a texture mask map in the training sample and input noise; wherein the coordinate map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference image in the clothing model; and the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model;

[0019] The optimization module is used to optimize the clothing texture map generation model based on the clothing features and the texture features.

[0020] According to another aspect of the present disclosure, a method for generating clothing for a digital character is provided, comprising:

[0021] Generate a clothing texture map of the digital character by using any one of the clothing texture map generation methods of the embodiments of the present disclosure;

[0022] The clothing of the digital character is generated using the clothing texture map of the digital character.

[0023] According to another aspect of the present disclosure, there is provided a digital character, comprising:

[0024] Digital clothing generated through clothing texture mapping;

[0025] This clothing texture map is generated using any of the above methods.

[0026] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0027] at least one processor; and

[0028] a memory communicatively connected to the at least one processor; wherein,

[0029] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any method in the embodiments of the present disclosure.

[0030] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any method according to the embodiments of the present disclosure.

[0031] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements any method according to the embodiments of the present disclosure when executed by a processor.

[0032] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0034] Figure 1 is a flow chart of a method for generating a clothing texture map according to an embodiment of the present disclosure;

[0035] Figure 2 is a flow chart of a method for generating a clothing texture map according to another embodiment of the present disclosure;

[0036] Figure 3 is a flow chart of a method for generating a clothing texture map according to another embodiment of the present disclosure;

[0037] Figure 4 It is a flowchart of a clothing texture map generation model training method according to an embodiment of the present disclosure;

[0038] Figure 5 is a flow chart of a clothing texture map generation model training method according to another embodiment of the present disclosure;

[0039] Figure 6 is a flow chart of a clothing texture map generation model training method according to another embodiment of the present disclosure;

[0040] Figure 7 is a flow chart of a clothing texture map generation model training method according to another embodiment of the present disclosure;

[0041] Figures 8a to 8d is a schematic diagram of data samples according to an embodiment of the present disclosure;

[0042] Fig. 9 is a schematic diagram of the network structure of an embodiment of the present disclosure;

[0043] Fig.10 is a schematic diagram of texture generation results in an embodiment of the present disclosure;

[0044] Fig.11 is a structural schematic diagram of a clothing texture map generating device according to an embodiment of the present disclosure;

[0045] Fig.12 is a structural schematic diagram of a clothing texture map generating device according to another embodiment of the present disclosure;

[0046] Fig.13 It is a structural schematic diagram of a clothing texture map generation model training device according to an embodiment of the present disclosure;

[0047] Fig.14 is a structural schematic diagram of a clothing texture map generation model training device according to another embodiment of the present disclosure;

[0048] Fig.15 is a method for generating clothing for a digital character according to another embodiment of the present disclosure;

[0049] Fig.16 It is a block diagram of an electronic device used to implement the clothing texture map generation method and clothing texture map generation model training method of the embodiments of the present disclosure. DETAILED DESCRIPTION

[0050] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0051] Figure 1 FIG. 1 is a flow chart of a method 100 for generating a clothing texture map according to an embodiment of the present disclosure, the method comprising:

[0052] S110, obtaining clothing features based on the clothing reference image.

[0053] S120, obtaining texture features according to a coordinate map and a texture mask map associated with the clothing reference image, wherein the coordinate map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference image in the clothing model; and the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model.

[0054] S130: Generate a clothing texture map based on the clothing feature and the texture feature.

[0055] In the disclosed embodiment, clothing may include but is not limited to clothing, shoes, hats, socks, gloves, scarves, ties, accessories, etc. The clothing reference image may also be referred to as a clothing rendering, which may include the style, color, pattern, style, etc. of the clothing that the digital character's clothing can present. The clothing reference image may be a two-dimensional image. The styles, colors, patterns, styles, etc. of different clothing may be different. For example, clothing styles may include clothes, pants, shoes, etc.; they may also include long sleeves, short sleeves, trousers, shorts, long skirts, short skirts, coats, etc. For another example, the style of clothing may be described by different design elements and structures, such as the style of long sleeves may include round necks, V-neck necks, trumpet sleeves, ordinary sleeves, etc. Based on the clothing reference image, clothing features related to one or more of the styles, colors, patterns, styles, etc. of clothing may be obtained.

[0056] In the disclosed embodiment, the associated coordinate mapping map and texture mask map are obtained based on the matching of the clothing reference map. Several three-dimensional clothing models can be saved in advance. Based on the three-dimensional clothing model, a clothing rendering map, a UV texture map (where U can be understood as a horizontal coordinate and V can be understood as a vertical coordinate), a coordinate mapping map and a texture mask map can be generated. Among them, the coordinate mapping map of the three-dimensional clothing model can include the coordinates corresponding to the UV texture map unfolded by the three-dimensional clothing model in the three-dimensional clothing model. The texture mask map of the three-dimensional clothing model includes an image generated based on the transparent channel in the texture map unfolded by the three-dimensional clothing model. For example, the texture mask map can be a binary image, and the transparent channel value of the pixel in the binary image is 0 or 1, wherein the transparent channel value of a pixel is 0, which represents that the pixel is completely transparent, and the transparent channel value of a pixel is 255, which represents that the pixel is completely opaque. If the transparent channel value of the pixel in the UV texture map is greater than or equal to 1, the transparent channel value of the pixel in the UV texture map can be set to 1, and the other pixels can be set to 0, so that the binary image can be obtained.

[0057] In one example, by comparing the similarity between the clothing reference image and the clothing rendering images of each three-dimensional clothing model, a three-dimensional clothing model matching the clothing reference image can be obtained. The matching three-dimensional clothing model is then expanded to obtain a UV texture map, and then a coordinate mapping map and a texture mask map associated with the clothing reference image are obtained based on the UV texture map.

[0058] In another example, clothing renderings, coordinate mappings, and texture mask maps of a plurality of three-dimensional clothing models are pre-saved. If the clothing reference image has a high degree of similarity with a clothing rendering of a certain three-dimensional clothing model, the coordinate mapping and texture mask map of the three-dimensional clothing model can be used as the coordinate mapping and texture mask map associated with the clothing reference image.

[0059] In the disclosed embodiment, after the texture features are obtained based on the coordinate mapping image and the texture mask image, a clothing texture map corresponding to the clothing reference image can be generated based on the clothing features and the texture features.

[0060] According to the embodiments of the present disclosure, clothing features and texture features can be obtained based on a clothing reference map, a coordinate mapping map and a texture mask map, and then a clothing texture map reflecting the clothing features and texture features can be quickly generated, which can reduce the time and cost of producing clothing texture maps and improve the flexibility and diversity of clothing texture design.

[0061] Figure 2 2 is a flow chart of a method 200 for generating a clothing texture map according to another embodiment of the present disclosure, and the method 200 can be used to implement steps S110 and S120 in the method 100 for generating a clothing texture map. In one embodiment, the method 200 includes: obtaining clothing features based on a clothing reference image, and further includes: S210, inputting the clothing reference image into a first network of a clothing texture map generation model to obtain the clothing features.

[0062] In one embodiment, method 200 also includes: obtaining texture features based on a coordinate mapping map and a texture mask map associated with the clothing reference image, and further includes: S220, inputting input noise, the coordinate mapping map and the texture mask map into a second network of a clothing texture map generation model to obtain the texture features.

[0063] In the disclosed embodiment, the clothing texture map generation model may include a first network and a second network, and the first network and the second network may use the same or similar neural network architecture (or referred to as a model framework). For example, the first network and the second network may adopt a U-shaped network (UNet) architecture. UNet is a convolutional neural network (CNN) architecture that uses a U-shaped network structure and jump connections. The specific training method of the clothing texture map generation model can be found in the description of the relevant embodiments below.

[0064] An example of a UNet structure mainly includes an encoder and a decoder. A connection bridge may be included between the two, and the connection bridge may connect the corresponding layers of the encoder and the decoder, which helps to restore the lost spatial information in the decoder. The encoder (also known as the contraction path) consists of a series of convolutional layers and pooling layers for feature extraction and downsampling. The encoder may include multiple convolutional blocks. Each convolutional block may include a convolutional layer, batch normalization, and activation functions, etc., which helps to learn the low-level features of the image. A pooling layer may also be included after each convolutional block. The decoder (also known as the expansion path) consists of a series of upsampling layers and convolutional layers for feature fusion and upsampling. The decoder may include multiple deconvolution blocks, each deconvolution block may include a deconvolutional layer, batch normalization, and activation functions, etc., which helps to learn the high-level semantic information of the image. After each deconvolution block, an upsampling layer may be added, corresponding to the pooling layer in the encoder. The output of the upsampling layer is concatenated with the feature map of the corresponding layer in the encoder to achieve feature fusion. Each layer in the decoder is connected to the corresponding layer in the encoder through skip connections, which helps to combine the semantic information of low-level and high-level layers.

[0065] In the embodiment of the present disclosure, the clothing rendering image is input into the first network of the clothing texture map generation model to obtain the clothing features of the clothing reference image. In the embodiment of the present disclosure, the input noise is the random noise generated in the process of processing the image by the clothing texture map generation model, and the input noise used for different clothing reference images may be different. The input noise and the coordinate mapping map and texture mask map associated with the clothing reference image are input into the second network of the clothing texture map generation model, and the texture features of the clothing reference image can be output. Clothing features and texture features can be understood as intermediate features of the clothing texture map generation model.

[0066] According to the embodiment of the present disclosure, the clothing features and texture features of the clothing reference image are combined and processed through the first network and the second network to generate a clothing texture map that is more consistent with the characteristics of the clothing reference image, which can reduce the production time of the clothing texture map and improve the generation efficiency of the clothing texture map.

[0067] Figure 3 3 is a flow chart of a method 300 for generating a clothing texture map according to another embodiment of the present disclosure, and the method 300 can be used to implement step S130 in the method 100 for generating a clothing texture map. In one embodiment, the method 300 includes: generating a clothing texture map based on the clothing feature and the texture feature, and further includes:

[0068] S310, splicing the clothing feature and the texture feature to obtain a splicing feature;

[0069] S320, inputting the splicing feature into the cross attention network of the second network to generate the clothing texture map.

[0070] In the disclosed embodiment, cross attention can dynamically adjust the attention of each modality (or sequence) to other modalities (or sequences) by calculating the similarity between the query vector of one modality (or sequence) and the key vector and value vector of another modality (or sequence), thereby realizing the comprehensive utilization of information. The clothing features and texture features can be spliced ​​and input into the cross attention network of the second network.

[0071] In the disclosed embodiment, after the clothing features and texture features are fused through the cross attention network of the second network, a clothing texture map that can reflect the clothing features and texture features of the clothing reference image can be further generated.

[0072] According to the embodiment of the present disclosure, the cross-attention network of the second network can realize the comprehensive utilization of clothing features and texture features, and generate a clothing texture map that is more in line with the characteristics of the clothing reference image.

[0073] In one embodiment, the method further comprises:

[0074] matching an associated clothing model according to the clothing reference image;

[0075] Based on the texture map unfolded by the clothing model, reverse query is performed on the coordinates of each point of the clothing model to obtain the coordinate mapping map associated with the clothing reference map;

[0076] Based on the transparent channel of the texture map unfolded by the clothing model, the texture mask map associated with the clothing reference map is obtained.

[0077] In an embodiment of the present disclosure, a number of three-dimensional clothing models can be pre-saved in a database. Based on a clothing reference image that can be input, a clothing model that can match the features of the clothing reference image can be searched from the database. In some examples, by comparing the similarity between the clothing reference image and the main perspective rendering of the three-dimensional clothing model, a three-dimensional clothing model that matches the clothing reference image can be obtained. For example, if the clothing reference image includes a white short-sleeved dress, a clothing model of the short-sleeved dress can be searched from the database. For another example, if the clothing reference image includes a short-sleeved round-neck T-shirt with a colorful pattern, a clothing model of the short-sleeved round-neck T-shirt can be searched in the database.

[0078] In the embodiment of the present disclosure, the three-dimensional model is composed of the vertices of all shapes in the three-dimensional space, and each vertex has unique coordinates in the three-dimensional space. By reversely querying the coordinates of each vertex in the matching three-dimensional model, a coordinate mapping diagram that can represent the shape of this three-dimensional model can be obtained.

[0079] In the disclosed embodiment, the points on the surface of the three-dimensional model can be mapped to a two-dimensional plane (e.g., UV space) through the automatic UV unfolding tool in the three-dimensional modeling software, and the three-dimensional model is UV unfolded to obtain a two-dimensional representation UV texture map based on the three-dimensional model, and then the coordinate mapping map and texture mask map of the UV map are obtained. During the UV unfolding process, each vertex on the surface of the three-dimensional model is assigned a UV coordinate. Based on these UV coordinates, the three-dimensional coordinates of each point on the three-dimensional model can be queried using rasterization technology, and the coordinate mapping map can be obtained by storing these three-dimensional coordinates. Rasterization technology is a technology that converts vertex data into fragments, which can convert an image into an image composed of grids, and each element corresponds to a pixel in the frame buffer. The texture mask map can be a binary image generated based on a transparent channel. The transparent channel can also be called an Alpha channel. The value of the transparent channel of each pixel (or transparent channel value, transparency value, etc.) ranges from 0 to 255. A transparent channel value of a pixel is 0, which represents that the pixel is completely transparent, and a transparent channel value of a pixel is 255, which represents that the pixel is completely opaque. The area where the value of the transparent channel in the UV texture map of the unfolded three-dimensional model is greater than a preset value, such as 1, can be regarded as a valid area of ​​the texture mask map.

[0080] According to the embodiment of the present disclosure, a coordinate mapping map and a texture mask map associated with the clothing reference image can be generated by matching the three-dimensional clothing model with the clothing reference image, and a clothing texture map that better conforms to the characteristics of the clothing reference image can be generated.

[0081] Figure 4 4 is a flow chart of a clothing texture map generation model training method 400 according to an embodiment of the present disclosure, the method comprising:

[0082] S410: Obtain clothing features based on clothing reference images in training samples.

[0083] S420, obtaining texture features according to the coordinate mapping map and texture mask map in the training sample and the input noise, wherein the coordinate mapping map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference image in the clothing model; and the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model.

[0084] S430: Optimizing the clothing texture map generation model based on the clothing feature and the texture feature.

[0085] In an embodiment of the present disclosure, a training sample may include a clothing reference image, a coordinate mapping image, and a texture mask image. The input noise may be a part of the training sample. The input noise may not be in the training sample, and may be noise randomly generated when using the training sample. After obtaining clothing features based on the clothing reference image, and obtaining texture features based on the coordinate mapping image and the texture mask image, real noise and predicted noise may be obtained based on the clothing features and the texture features. The loss value of the loss function of the clothing texture map generation model is calculated using the real noise and the predicted noise, and based on the loss value, it may be determined whether to optimize the clothing texture map generation model. For example, if the loss value does not converge, the loss function of the model is iterated by adjusting the parameters of the clothing texture map generation model until the clothing texture map generation model can achieve the expected training effect, such as the convergence of the loss value.

[0086] According to the embodiments of the present disclosure, the clothing texture map generation model is optimized and trained by using real noise and predicted noise, so that the training quality of the clothing texture map generation model can be improved.

[0087] Figure 5 It is a flowchart of a clothing texture map generation model training method 500 according to another embodiment of the present disclosure, and the method 500 can be used to implement step S410 and step S420 in the clothing texture map generation model training method 400. In one embodiment, the method 500 includes: in one embodiment, obtaining clothing features based on clothing reference images in training samples, further including: S510, inputting the clothing reference image into the first network of the clothing texture map generation model to obtain the clothing features;

[0088] In one embodiment, method 500 includes: obtaining texture features based on the input noise, the coordinate mapping map and the texture mask map in the training sample, and further includes: S520, inputting the input noise, the coordinate mapping map and the texture mask map into a second network of a clothing texture map generation model to obtain the texture features.

[0089] In the embodiment of the present disclosure, the method of obtaining clothing features and texture features can refer to the relevant description in the clothing texture map generation method above, which will not be repeated here.

[0090] According to the embodiment of the present disclosure, the clothing features and texture features of the clothing reference image in the sample are combined and processed through the first network and the second network, so that the trained model can generate a clothing texture map that is more in line with the characteristics of the clothing reference image, which can reduce the production time of the clothing texture map and improve the generation efficiency of the clothing texture map.

[0091] Figure 6is a flow chart of a clothing texture map generation model training method 600 according to another embodiment of the present disclosure, and the method 600 can be used to implement step S430 in the clothing texture map generation model training method 400. In one embodiment, the method 600 includes: optimizing the clothing texture map generation model based on the clothing feature and the texture feature, and further includes;

[0092] S610, splicing the clothing feature and the texture feature to obtain a splicing feature;

[0093] S620, inputting the concatenated features into the cross attention network of the second network;

[0094] S630, iteratively processing the splicing feature through the second network;

[0095] S640: Optimize the clothing texture map generation model based on the first noise added and the second noise removed in the iterative process.

[0096] In the disclosed embodiment, the splicing feature is input into the cross-attention network of the second network, and the cross-attention mechanism of the cross-attention network is used to iteratively process the splicing feature. In the iterative process, the noise added to the splicing feature can be considered as real noise, and the noise removed from the final noisy image can be considered as predicted noise. Based on the added noise and the removed noise, the loss value of the loss function of the clothing texture map generation model is calculated, and based on the loss value, it can be determined whether the clothing texture map generation model can be optimized. If the loss value does not converge, the loss function of the model is iterated by adjusting the parameters of the clothing texture map generation model until the loss value of the clothing texture map generation model converges.

[0097] According to the embodiment of the present disclosure, the stitching features are iteratively processed through the clothing texture map generation model to obtain the second noise, which can improve the training quality of the clothing texture map generation model.

[0098] In one embodiment, the splicing feature is iteratively processed by the second network, including:

[0099] The splicing feature is subjected to multi-stage iterative processing by the second network to obtain an added first noise and a removed second noise; wherein the multi-stage iterative processing includes a plurality of consecutive forward diffusion steps and a plurality of consecutive backward diffusion steps; the plurality of consecutive forward diffusion steps are used to iteratively add noise to the splicing feature to obtain a noisy target image, and the first noise includes the noise added in the plurality of consecutive forward diffusion steps; the plurality of consecutive backward diffusion steps are used to iteratively remove noise from the target image to obtain a restored texture map, and the second noise includes the noise removed in the plurality of consecutive backward diffusion steps.

[0100] In the disclosed embodiment, a Wensheng graph tool, such as an AI painting generation tool based on a diffusion model, can be used to process the splicing features to obtain the added first noise and the removed second noise. The splicing features are input into the second network for multi-stage iterative processing. For example, the multi-stage iterative processing may include a plurality of consecutive forward diffusion steps (or forward noise addition steps) and a plurality of consecutive reverse diffusion steps (or reverse denoising steps).

[0101] For example, in a forward diffusion step, noise is first added to the splicing feature to obtain a first noisy image, and in the next forward diffusion step, noise is added to the first noisy image to obtain a second noisy image, and so on, and multiple forward diffusion steps are continuously performed until a noisy target image is obtained. In the process of multiple consecutive forward diffusion steps, the sum of the noise added in each forward diffusion step can be calculated to obtain the first noise; or the first noise can be obtained based on the difference between the target image and the splicing feature. For another example, in a reverse diffusion step, noise is first removed from the target image to obtain a first denoised image, and in the next reverse diffusion step, noise is removed from the first denoised image to obtain a second denoised image, and so on, and multiple reverse diffusion steps are continuously performed until a restored texture map is obtained. In the process of multiple consecutive reverse diffusion steps, the sum of the noise removed in each reverse diffusion step can be calculated to obtain the second noise; or the second noise can be obtained based on the difference between the restored texture map and the target image. Through the above forward diffusion steps, noise, such as random Gaussian noise, can be introduced into the image generated by the model, and the input random Gaussian noise can be gradually converted into a noisy target image. The added random Gaussian noise is usually different from the input noise of the clothing texture map generation model. The noise in the image can be removed through the above-mentioned back diffusion step. For example, some specific samplers can be used to iteratively denoise the target image and finally obtain a UV texture map similar to the one in the database.

[0102] According to the embodiments of the present disclosure, the efficiency of model training can be improved by optimizing the model by adding noise and removing noise in multi-stage iterations.

[0103] Figure 7 7 is a flow chart of a clothing texture map generation model training method 700 according to another embodiment of the present disclosure, which can be used to implement step S440 in the clothing texture map generation model training method 400. In one embodiment, the method 700 includes optimizing the clothing texture map generation model based on the first noise added and the second noise removed in the iterative process, and further includes:

[0104] S710, calculating a loss function based on the first noise and the second noise;

[0105] S720: Adjust parameters of the second network based on the loss function until the loss function converges.

[0106] In the disclosed embodiment, the noise added and the noise removed during the iteration process are substituted into the loss function of the clothing texture map generation model to calculate the loss value. For example, the loss function can use the mean square error (MSE) and other forms to measure the difference between the noise predicted by the model and the real noise. The real noise may include the noise added in the forward diffusion (i.e., forward diffusion), such as the input noise. The predicted noise may include the noise used for denoising calculated or predicted when iterative denoising is performed by the sampler in the reverse diffusion.

[0107] An example of a loss function calculation formula is shown below:

[0108]

[0109] Where t represents a given time step, x represents the noisy image received by the model, ∈ pred represents the prediction of the initial noise (i.e. the removed noise), ∈ true Represents the real noise (i.e. the added noise), and it is expected that E can be performed on all training samples, noise samples, and time steps. Adjust the parameters of the model to minimize the loss function to complete the convergence of the loss function Loss.

[0110] According to an embodiment of the present disclosure, by calculating the loss function of the clothing texture map generation model to adjust the parameters of the clothing texture map generation model, the training efficiency of the clothing texture map generation model can be improved. The trained clothing texture map generation model can generate a clothing texture map that conforms to the characteristics of the input image, such as a clothing reference image.

[0111] The present disclosure provides a texture map generation solution, including:

[0112] 1. Dataset

[0113] A batch of 3D models can be pre-generated based on common clothing types, such as 3D models of T-shirts, dresses, hoodies, shorts and skirts. Each model can have a fixed UV unwrapping and multiple different high-quality texture maps. Model UV unwrapping is the process of flattening the surface of a 3D model onto a 2D plane so that textures can be applied. Texture maps can be color images with a transparency channel.

[0114] Collect the required data. For example, Figures 8a to 8d As shown, each set of data samples may include the following four types of images, and the resolution may be 512*512.

[0115] in, Figure 8a This is a model's positive perspective rendering: a color image with a transparent channel, rendered based on the 3D model at a fixed camera perspective.

[0116] Figure 8b It is a UV texture map: a color image with a transparent channel, an existing designed texture.

[0117] Figure 8c It is a coordinate map: each pixel stores the 3D coordinates of each point of the corresponding 3D model. The coordinate map is made by using the rasterization principle to reversely query the coordinates of each 3D point of the model from the UV map, and store these 3D coordinates separately into an independent image.

[0118] Figure 8d The texture mask map is a binary image corresponding to the transparent channel of the UV texture map. For example, the transparent channel value of the pixels in the texture mask map is 1 or 0, where the area with a value of 1 can correspond to the opaque area of ​​the texture map.

[0119] 2. Network Model

[0120] The model structure is as follows Fig. 9 As shown, the input is a clothing reference image, random noise, a coordinate map and a texture mask map, and the output is a UV texture map.

[0121] An example of a model network architecture includes a dual-path UNet structure:

[0122] (1) UVNet, using UNet as the model framework, based on the SDXL pre-trained weights as the basic model, and integrating random noise, coordinate mapping, and texture mask Figure 3 The random noise is the standard input of the diffusion paradigm, the texture mask can provide shape and contour priors for texture generation, and the coordinate map strengthens the mapping relationship between the model 3D position semantic priors and 2D texture expansion.

[0123] (2) ClothNet, which is used to encode clothing features. Its structure can replicate the backbone UNet. For example, it uses the pre-trained parameters of the large-scale stable diffusion (SDXL) and uses the diffusion paradigm to finetune on massive clothing data.

[0124] Loss function: Stable Diffusion is an image generation method based on a diffusion model, which gradually converts noise into an image through an iterative process. This process can be divided into multiple stages, each of which includes a forward diffusion step and a backward diffusion step. The forward diffusion step gradually introduces noise into the image, while the backward diffusion step gradually removes the noise. In addition, the predicted noise can be obtained based on the noise removed by the backward diffusion step. When training the UNet network, the main role of the loss function is to guide the model to accurately restore the image during the reverse denoising process. For example, a loss function can be the mean square error (MSE), which is used to measure the difference between the noise predicted by the model and the actual noise.

[0125] (3) The attention mechanism is used to promote the interaction between the original UNet clothing features and texture features, and finally generate a complete texture map.

[0126] Cross attention interaction: The ClothNet network weights are fixed, the clothing features extracted by ClothNet and the texture features extracted by UVNet are connected, and then input into UVNet through the cross attention mechanism, and the weights of UVNet are trained and updated according to the loss function.

[0127] Some experimental results such as Fig.10 As shown. Input the clothing reference image of a short-sleeved shirt, random noise, coordinate mapping map and texture mask map into the network to output the texture map of the unfolded short-sleeved shirt. Input the clothing reference image of a long-sleeved sweater, random noise, coordinate mapping map and texture mask map into the network to output the texture map of the unfolded long-sleeved sweater top. Input the clothing reference image of a short-sleeved cheongsam, random noise, coordinate mapping map and texture mask map into the network to output the texture map of the unfolded short-sleeved cheongsam.

[0128] Fig.11 is a structural schematic diagram of a clothing texture map generating device 1100 according to an embodiment of the present disclosure. The device 1100 may include:

[0129] A clothing feature acquisition module 1110 is used to obtain clothing features based on a clothing reference image;

[0130] The texture feature acquisition module 1120 is used to obtain texture features according to a coordinate map and a texture mask map associated with the clothing reference image; wherein the coordinate map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference image in the clothing model; and the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model;

[0131] The clothing map generation module 1130 is used to generate a clothing texture map based on the clothing features and the texture features.

[0132] Fig.12 It is a structural schematic diagram of a clothing texture map generation device 1200 according to another embodiment of the present disclosure, and the device 1200 includes: a clothing feature acquisition module 1210, a texture feature acquisition module 1220 and a clothing map generation module 1230. The functions of the above modules can refer to the functions of each module of the clothing texture map generation device of the above embodiment. In one embodiment, the clothing feature acquisition module 1210 is used to input the clothing reference image into the first network of the clothing texture map generation model to obtain the clothing feature; the texture feature acquisition module 1220 is used to input the input noise, the coordinate mapping map and the texture mask map into the second network of the clothing texture map generation model to obtain the texture feature.

[0133] In one embodiment, the clothing map generation module 1230 includes:

[0134] A splicing submodule 1231 is used to splice the clothing feature and the texture feature to obtain a splicing feature;

[0135] The generating submodule 1232 is used to input the splicing feature into the cross attention network of the second network to generate the clothing texture map.

[0136] In one embodiment, it further includes:

[0137] A matching module 1240, for matching an associated clothing model according to the clothing reference image;

[0138] A coordinate mapping module 1250 is used to perform a reverse query on the coordinates of each point of the clothing model based on the texture map developed by the clothing model to obtain the coordinate mapping map associated with the clothing reference map;

[0139] The texture mask module 1260 is used to obtain the texture mask map associated with the clothing reference map based on the transparent channel of the texture map unfolded by the clothing model.

[0140] Fig.13 1 is a schematic diagram of a clothing texture map generation model training device 1300 according to an embodiment of the present disclosure. The device 1300 may include:

[0141] A clothing feature acquisition module 1310 is used to obtain clothing features based on clothing reference images in training samples;

[0142] The texture feature acquisition module 1320 is used to obtain texture features according to the coordinate map and texture mask map in the training sample and the input noise; wherein the coordinate map includes the coordinates of the texture map unfolded by the clothing model associated with the clothing reference image corresponding to the clothing model in the clothing model; the texture mask map includes an image generated based on the transparent channel in the texture map unfolded by the clothing model;

[0143] The optimization module 1330 is used to optimize the clothing texture map generation model based on the clothing features and the texture features.

[0144] Fig.14 It is a structural schematic diagram of a clothing texture map generation model training device 1400 according to another embodiment of the present disclosure, and the device 1400 includes: a clothing feature acquisition module 1410, a texture feature acquisition module 1420 and an optimization module 1430. The functions of the above modules can refer to the functions of each module of the clothing texture map generation model training device in the above embodiment. In one embodiment, the clothing feature acquisition module 1410 is used to input the clothing reference image into the first network of the clothing texture map generation model to obtain the clothing feature; the texture feature acquisition module 1420 is used to input the input noise, the coordinate mapping map and the texture mask map into the second network of the clothing texture map generation model to obtain the texture feature.

[0145] In one embodiment, the optimization module 1430 includes:

[0146] A splicing submodule 1431 is used to splice the clothing feature and the texture feature to obtain a splicing feature;

[0147] An input submodule 1432, for inputting the concatenated features into the cross attention network of the second network;

[0148] An iterator module 1433, used for iteratively processing the splicing feature through the second network;

[0149] The optimization submodule 1434 is used to optimize the clothing texture map generation model based on the first noise added and the second noise removed in the iterative process.

[0150] In one embodiment, the iterative submodule 1433 is used to perform multi-stage iterative processing on the splicing feature through the second network to obtain an added first noise and a removed second noise; wherein the multi-stage iterative processing includes a plurality of consecutive forward diffusion steps and a plurality of consecutive backward diffusion steps; the plurality of consecutive forward diffusion steps are used to iteratively add noise to the splicing feature to obtain a noisy target image, and the first noise includes the noise added in the plurality of consecutive forward diffusion steps; the plurality of consecutive backward diffusion steps are used to iteratively remove noise from the target image to obtain a restored texture map, and the second noise includes the noise removed in the plurality of consecutive backward diffusion steps.

[0151] In one implementation, the optimization submodule 1434 is used to calculate a loss function based on the first noise and the second noise; and adjust parameters of the second network based on the loss function until the loss function converges.

[0152] For the description of specific functions and examples of each module and submodule of the device in the embodiment of the present disclosure, reference can be made to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0153] Fig.15 A method for generating clothing for a digital character according to another embodiment of the present disclosure includes:

[0154] S1510, generating a clothing texture map of a digital character by using any one of the clothing texture map generation methods in the above embodiments;

[0155] S1520: Generate clothing for the digital character using the clothing texture map of the digital character.

[0156] In the disclosed embodiments, the digital character may be a digital person or other digital object. After the model is trained using the training method for generating a clothing texture map model in the above-mentioned embodiment, the model may be used to generate a clothing texture map for the digital character. Then, the clothing texture map may be used to add clothes to the digital character. In this process, the size, direction, position, etc. of the clothing texture map of the digital character may be adjusted according to the size and shape of the digital character model, so that the clothing texture map is adapted to the digital character.

[0157] The disclosed embodiments also provide a digital character, including: digital clothing generated by clothing texture mapping; generated by using any one of the clothing texture mapping generation methods in the above embodiments.

[0158] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0159] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0160] Fig.16 A schematic block diagram of an example electronic device 1600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0161] like Fig.16 As shown, the device 1600 includes a computing unit 1601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1602 or a computer program loaded from a storage unit 1608 into a random access memory (RAM) 1603. In the RAM 1603, various programs and data required for the operation of the device 1600 can also be stored. The computing unit 1601, the ROM 1602, and the RAM 1603 are connected to each other via a bus 1604. An input / output (I / O) interface 1605 is also connected to the bus 1604.

[0162] A number of components in the device 1600 are connected to the I / O interface 1605, including: an input unit 1606, such as a keyboard, a mouse, etc.; an output unit 1607, such as various types of displays, speakers, etc.; a storage unit 1608, such as a disk, an optical disk, etc.; and a communication unit 1609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1609 allows the device 1600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0163] The computing unit 1601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1601 performs the various methods and processes described above, such as a clothing texture map generation method and a clothing texture map generation model training method. For example, in some embodiments, the clothing texture map generation method and the clothing texture map generation model training method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1600 via the ROM 1602 and / or the communication unit 1609. When the computer program is loaded into the RAM 1603 and executed by the computing unit 1601, one or more steps of the clothing texture map generation method and the clothing texture map generation model training method described above may be performed. Alternatively, in other embodiments, the computing unit 1601 may be configured to execute the clothing texture map generation method and the clothing texture map generation model training method in any other appropriate manner (eg, by means of firmware).

[0164] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0165] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0166] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0167] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0168] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0169] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0170] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0171] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating a clothing texture map, comprising: Obtain clothing features based on a clothing reference image; The texture feature is obtained according to a coordinate map and a texture mask map associated with the clothing reference map; wherein the coordinate map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference map in the clothing model; and the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model; A clothing texture map is generated based on the clothing features and the texture features.

2. The method according to claim 1, wherein: Obtaining clothing features based on a clothing reference image, including: inputting the clothing reference image into a first network of a clothing texture map generation model to obtain the clothing features; The texture feature is obtained according to the coordinate mapping map and the texture mask map associated with the clothing reference map, including: inputting the input noise, the coordinate mapping map and the texture mask map into the second network of the clothing texture map generation model to obtain the texture feature.

3. The method according to claim 2, wherein: Generating a clothing texture map based on the clothing feature and the texture feature, including: Splicing the clothing feature and the texture feature to obtain a splicing feature; The splicing features are input into the cross attention network of the second network to generate the clothing texture map.

4. The method according to claim 3, further comprising: matching the associated clothing model according to the clothing reference image; Based on the texture map unfolded by the clothing model, reverse query is performed on the coordinates of each point of the clothing model to obtain the coordinate mapping map associated with the clothing reference map; The texture mask map associated with the clothing reference map is obtained based on the transparent channel of the texture map unfolded by the clothing model.

5. A clothing texture map generation model training method, comprising: Obtain clothing features based on clothing reference images in training samples; According to the coordinate mapping map and the texture mask map in the training sample and the input noise, the texture feature is obtained; wherein the coordinate mapping map includes the coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference image in the clothing model; the texture mask map includes an image generated based on the transparent channel in the texture map unfolded by the clothing model; Based on the clothing features and the texture features, the clothing texture map generation model is optimized.

6. The method according to claim 5, wherein: Obtaining clothing features based on clothing reference images in training samples, including: inputting the clothing reference images into a first network of a clothing texture map generation model to obtain the clothing features; Based on the coordinate mapping map and the texture mask map in the training sample and the input noise, texture features are obtained, including: inputting the input noise, the coordinate mapping map and the texture mask map into a second network of a clothing texture map generation model to obtain the texture features.

7. The method according to claim 6, wherein: Based on the clothing features and the texture features, optimizing the clothing texture map generation model, including: Splicing the clothing feature and the texture feature to obtain a splicing feature; Inputting the concatenated features into the criss-cross attention network of the second network; Iteratively processing the splicing features through the second network; The clothing texture map generation model is optimized based on the first noise added and the second noise removed in the iterative process.

8. The method according to claim 7, wherein: Iteratively processing the splicing features through the second network includes: The stitching features are subjected to multi-stage iterative processing by the second network to obtain an added first noise and a removed second noise; wherein the multi-stage iterative processing includes a plurality of consecutive forward diffusion steps and a plurality of consecutive backward diffusion steps; the plurality of consecutive forward diffusion steps are used to iteratively add noise to the stitching features to obtain a noisy target image, and the first noise includes the noise added in the plurality of consecutive forward diffusion steps; the plurality of consecutive backward diffusion steps are used to iteratively remove noise from the target image to obtain a restored texture map, and the second noise includes the noise removed in the plurality of consecutive backward diffusion steps.

9. The method according to claim 7 or 8, wherein: Based on the first noise added and the second noise removed in the iterative process, the clothing texture map generation model is optimized, including: Calculating a loss function based on the first noise and the second noise; The parameters of the second network are adjusted based on the loss function until the loss function converges.

10. A clothing texture map generating device, comprising: A clothing feature acquisition module, used to obtain clothing features based on a clothing reference image; A texture feature acquisition module, configured to obtain texture features according to a coordinate map and a texture mask map associated with the clothing reference map; wherein the coordinate map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference map in the clothing model; and the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model; The clothing map generation module is used to generate a clothing texture map based on the clothing features and the texture features.

11. The device according to claim 10, wherein: The clothing feature acquisition module is used to input the clothing reference image into the first network of the clothing texture map generation model to obtain the clothing feature; the texture feature acquisition module is used to input the input noise, the coordinate mapping image and the texture mask image into the second network of the clothing texture map generation model to obtain the texture feature.

12. The device according to claim 11, wherein The clothing map generation module includes: A splicing submodule, used for splicing the clothing feature and the texture feature to obtain a splicing feature; A generation submodule is used to input the splicing features into the cross attention network of the second network to generate the clothing texture map.

13. The device according to claim 12, wherein: Also includes: A matching module, used for matching the associated clothing model according to the clothing reference image; A coordinate mapping module, configured to perform a reverse query on the coordinates of each point of the clothing model based on the texture map unfolded by the clothing model, so as to obtain the coordinate mapping map associated with the clothing reference map; The texture mask module is used to obtain the texture mask map associated with the clothing reference map based on the transparent channel of the texture map unfolded by the clothing model.

14. A clothing texture map generation model training device, comprising: A clothing feature acquisition module, used to obtain clothing features based on clothing reference images in training samples; A texture feature acquisition module, configured to obtain texture features according to a coordinate map and a texture mask map in the training sample and input noise; wherein the coordinate map includes coordinates corresponding to the texture map unfolded by the clothing model associated with the clothing reference image in the clothing model; and the texture mask map includes an image generated based on a transparent channel in the texture map unfolded by the clothing model; The optimization module is used to optimize the clothing texture map generation model based on the clothing features and the texture features.

15. The device according to claim 14, wherein: The clothing feature acquisition module is used to input the clothing reference image into the first network of the clothing texture map generation model to obtain the clothing feature; the texture feature acquisition module is used to input the input noise, the coordinate mapping image and the texture mask image into the second network of the clothing texture map generation model to obtain the texture feature.

16. The device according to claim 15, wherein: The optimization module comprises: A splicing submodule, used for splicing the clothing feature and the texture feature to obtain a splicing feature; An input submodule, used for inputting the concatenated features into a cross-attention network of the second network; An iterative submodule, used for iteratively processing the splicing features through the second network; The optimization submodule is used to optimize the clothing texture map generation model based on the first noise added and the second noise removed in the iterative process.

17. The device according to claim 16, wherein: The iterative submodule is used to perform multi-stage iterative processing on the splicing features through the second network to obtain an added first noise and a removed second noise; wherein the multi-stage iterative processing includes a plurality of consecutive forward diffusion steps and a plurality of consecutive backward diffusion steps; the plurality of consecutive forward diffusion steps are used to iteratively add noise to the splicing features to obtain a noisy target image, and the first noise includes the noise added in the plurality of consecutive forward diffusion steps; the plurality of consecutive backward diffusion steps are used to iteratively remove noise from the target image to obtain a restored texture map, and the second noise includes the noise removed in the plurality of consecutive backward diffusion steps.

18. The device according to claim 16 or 17, wherein: The optimization submodule is used to calculate a loss function based on the first noise and the second noise; and adjust parameters of the second network based on the loss function until the loss function converges.

19. A method for generating clothing for a digital character, comprising: Generating a clothing texture map of the digital character by the method according to any one of claims 1 to 4; The clothing of the digital character is generated by using the clothing texture map of the digital character.

20. A digital character, comprising: Digital clothing generated through clothing texture mapping; The clothing texture map is generated by using the method described in any one of claims 1-4.

21. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images