Method and device for generating clothing picture with human model with specified effect

Abstract

The invention provides a method and device for generating a human model clothing picture with a specified effect, and the method comprises the steps: taking a three-dimensional picture containing clothing and a three-dimensional picture of digital human model wearing clothing as input, and carrying out the rendering of the three-dimensional picture of the digital human model wearing clothing according to an effect specified by a user, so as to obtain a first rendered image, and processing the first rendered image based on the three-dimensional picture containing the clothing to obtain a processed image, and generating a plurality of clothing pictures with a human model and a specified effect based on the processed image. According to the scheme provided by the invention, the picture can be rendered according to the effect specified by the user, the personalized demand of the user is fully considered in the generation process, the generated picture better conforms to the thought of the user, compared with a traditional template type generation method, the method is more flexible and free, and meanwhile, the rendering method based on the three-dimensional picture is adopted, so that the user experience is improved. And the generated picture is more real and has better texture.

Description

Technical Field

[0001] The invention belongs to the technical field of three-dimensional modeling, and in particular relates to a method and a device for generating a clothing picture with a human model of a specified effect. Background Art

[0002] In the fields of clothing design, display and sales, the application of digital technology is becoming more and more extensive. At present, digital clothing design and display based on three-dimensional models has become a mainstream technology, which is conducive to saving costs, improving efficiency and reducing waste, and is therefore favored by designers and merchants.

[0003] Digital clothing design technology is generally divided into two categories: one is to directly draw a two-dimensional plane, use computer-aided design software to generate clothing design drawings, and achieve display effects through simulated fitting and lighting effects; the other is based on three-dimensional clothing models, through three-dimensional rendering and simulation technology to generate clothing pictures with human models, in order to present a more realistic and intuitive effect.

[0004] At present, digital clothing design and display based on 3D models have attracted more and more attention in the clothing industry and have become an essential technology. Existing related technologies have used 3D rendering technology to render and generate 2D images in multiple scenarios, including scene simulation and character visualization effects in film and television film production, multimedia advertising, and human-virtual object interaction in VR / AR devices. At the same time, commercial software can also automatically remove the background after rendering and output PNG format images.

[0005] However, the existing digital clothing design technology still has many shortcomings. The most important problem is that it provides users with fewer choices and lacks personalization and customization. That is, it is impossible to generate unique clothing design drawings that meet the user's requirements based on the user's ideas, and the generated results are difficult to guarantee that they meet the user's actual needs and preferences. Summary of the invention

[0006] In order to overcome the defects of the above-mentioned prior art, the present invention proposes a method for generating a human model clothing picture with a specified effect, the method comprising:

[0007] Taking the three-dimensional picture containing the clothing and the three-dimensional picture of the digital human model wearing the clothing as input, rendering the three-dimensional picture of the digital human model wearing the clothing according to the effect specified by the user to obtain a first rendered image;

[0008] Based on the three-dimensional picture including the clothing, processing the first rendered image to obtain a processed image;

[0009] Based on the processed image, a plurality of pictures of the clothing with human models having a specified effect are generated.

[0010] Specifically, rendering the three-dimensional picture of the digital human model wearing the clothing according to the specified effect includes:

[0011] Rendering the model in the three-dimensional picture of the digital human model wearing the clothing based on the effect in the first reference sample specified by the user;

[0012] Based on the effect in the second reference sample specified by the user, the background in the three-dimensional picture of the digital human model wearing the clothing is rendered.

[0013] Optionally, the first reference sample includes a model reference picture and / or a model style entry, and the second reference sample includes a background reference picture and / or a background style entry.

[0014] Preferably, the first reference sample and the second reference sample are generated based on a three-dimensional picture containing the clothing, are preset, or are input by the user.

[0015] Optionally, the processing the first rendered image based on the three-dimensional picture containing the clothing to obtain a processed image includes:

[0016] Based on the three-dimensional picture containing the clothing, identifying the range of the clothing in the first rendering image to obtain a clothing identification map;

[0017] Based on the three-dimensional picture containing the clothing, the clothing in the clothing identification image is rendered offline to obtain a processed image.

[0018] Optionally, the processing the first rendered image based on the three-dimensional picture containing the clothing to obtain a processed image includes:

[0019] Based on the three-dimensional picture containing the clothing, offline rendering is performed on the clothing in the first rendering image to obtain a second rendering image;

[0020] Based on the three-dimensional picture containing the clothing, the range of the clothing in the second rendered image is identified to obtain the processed image.

[0021] Preferably, the clothing picture with the human model of the specified effect is generated based on the AIGC algorithm of stable diffusion.

[0022] The present invention also proposes a device for generating a picture of a human model wearing clothing with a specified effect, the device comprising:

[0023] a rendering module, for taking the three-dimensional picture containing the clothing and the three-dimensional picture of the digital human model wearing the clothing as input, and rendering the three-dimensional picture of the digital human model wearing the clothing according to the effect specified by the user to obtain a first rendered image;

[0024] a processing module, configured to process the first rendered image based on the three-dimensional picture containing the garment to obtain a processed image;

[0025] A generation module is used to generate a plurality of clothing pictures with human models of specified effects based on the processed images.

[0026] Specifically, the rendering module includes:

[0027] A first rendering unit, configured to render a model in a three-dimensional picture of a digital human model wearing the clothing based on an effect in the first reference sample specified by the user;

[0028] The second rendering unit is used to render the background in the three-dimensional picture of the digital human model wearing the clothing based on the effect in the second reference sample specified by the user.

[0029] Specifically, the processing module includes:

[0030] A third rendering unit, configured to perform offline rendering on an image based on the three-dimensional picture containing the garment;

[0031] The recognition unit is used to recognize the range of the clothing in the image based on the three-dimensional picture containing the clothing.

[0032] The present invention has at least the following beneficial effects:

[0033] The solution proposed in the present invention allows users to specify different effect requirements to generate clothing pictures according to their own needs and preferences, and can achieve personalized customization. The generated clothing pictures with human models are more realistic and lifelike, which greatly improves the authenticity and objectivity of the images. The solution proposed in the present invention can be used in other similar scenarios such as jewelry display and furniture design, and has high universality and practicality.

[0034] Furthermore, the specified effects in the solution proposed in the present invention include optional reference samples and style entries, and both models and backgrounds can be rendered, which increases the user's freedom and flexibility in customization. The offline rendering of clothing effectively reduces the amount of calculation and processing time during processing, improves processing efficiency, and uses recognition technology to realize automatic and rapid recognition of clothing contained in sample images.

[0035] Therefore, the present invention provides a method and device for generating pictures of clothing with human models of specified effects. The scheme proposed by the present invention can render pictures according to the effects specified by the user. The personalized needs of the user are fully considered in the generation process, so that the generated pictures are more in line with the user's ideas. Compared with the traditional template generation method, it is more flexible and free. At the same time, a rendering method based on three-dimensional pictures is adopted, so that the generated pictures are more realistic and have better texture. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 A schematic flow chart of a method for generating a picture of clothing with a human model having a specified effect provided in Example 1;

[0038] Figure 2 is a schematic flow chart of a method for processing the first rendered image;

[0039] Figure 3 is a flowchart of another method for processing the first rendered image;

[0040] Figure 4 This is a schematic diagram of the module structure of the device for generating a picture of a human model wearing clothing with a specified effect provided in Example 2.

[0041] Reference numerals

[0042] 21 - rendering module; 22 - processing module; 23 - generating module; 211 - first rendering unit; 212 - second rendering unit; 221 - third rendering unit; 222 - identification unit. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Hereinafter, various embodiments of the present invention will be described more fully. The present invention may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present invention to the specific embodiments disclosed herein, but the present invention should be understood to cover all adjustments, equivalents and / or alternatives falling within the spirit and scope of the various embodiments of the present invention.

[0045] Hereinafter, the term "include" or "may include" used in various embodiments of the present invention indicates the presence of disclosed functions, operations or elements, and does not limit the addition of one or more functions, operations or elements. In addition, as used in various embodiments of the present invention, the terms "include", "have" and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0046] In various embodiments of the present invention, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the words listed at the same time. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0047] The expressions (such as "first", "second", etc.) used in various embodiments of the present invention may modify the various constituent elements in various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used for the purpose of distinguishing an element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of various embodiments of the present invention, the first element may be referred to as the second element, and similarly, the second element may also be referred to as the first element.

[0048] It should be noted that in the present invention, unless otherwise clearly specified and defined, the terms such as "installation", "connection", "fixation" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] In the present invention, those skilled in the art need to understand that the terms indicating orientation or positional relationship herein are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0050] The terms used in various embodiments of the present invention are only used for the purpose of describing specific embodiments and are not intended to limit various embodiments of the present invention. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise limited, all terms used here (including technical terms and scientific terms) have the same meaning as the meaning generally understood by those of ordinary skill in the art to which the various embodiments of the present invention belong. The terms (such as the terms defined in the dictionary generally used) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in various embodiments of the present invention.

[0051] Example 1

[0052] See also Figure 1 This embodiment proposes a method for generating a human model clothing picture with a specified effect, the method comprising:

[0053] S100: taking the three-dimensional image containing the clothing and the three-dimensional image of the digital human model wearing the clothing as input, rendering the three-dimensional image of the digital human model wearing the clothing according to the effect specified by the user to obtain a first rendered image.

[0054] S200: Based on the three-dimensional picture containing the clothing, the first rendered image is processed to obtain a processed image.

[0055] S300: Based on the processed image, generate a plurality of clothing pictures with human models of specified effects.

[0056] Specifically, the step S100 of rendering the three-dimensional image of the digital human model wearing clothing according to the specified effect includes:

[0057] Rendering the model in the three-dimensional picture of the digital human model wearing the clothing based on the effect in the first reference sample specified by the user;

[0058] Based on the effect in the second reference sample specified by the user, the background in the three-dimensional picture of the digital human model wearing the clothing is rendered.

[0059] Optionally, the first reference sample includes a model reference picture and / or a model style entry, and the second reference sample includes a background reference picture and / or a background style entry.

[0060] It should be noted that the rendering model and background based on the entry adopts the text-to-image generation technology, which uses a deep neural network to convert a given text description into a corresponding image. The text is input into a pre-trained language model that can convert natural language text into a vector representation, and then the vector is input into an image generation model. This model can generate the corresponding image based on the input vector. The final generated image can also be adjusted and improved according to the specific content of the entry;

[0061] Image style transfer technology is usually used to render models and backgrounds based on pictures. The deep neural network is used to transfer the input image style to the image to be rendered. Specifically, the convolutional neural network is used to extract the features of each image for preprocessing, and then the deconvolutional neural network (DCNN) is used to reconstruct these feature information into a new image.

[0062] In addition, if the background is rendered based on only one image, this image can be directly used as the background in the three-dimensional picture of the digital human model wearing the clothing.

[0063] Preferably, the first reference sample and the second reference sample are generated based on a three-dimensional image containing clothing, pre-set or input by the user. The first reference sample and the second reference sample may contain multiple images and / or entries for the user to use, and the user can select several of the images and / or entries as the basis for rendering the model and background in the image.

[0064] It should be noted that the generation of the first reference sample and the second reference sample based on the three-dimensional image containing clothing is specifically achieved through the recognition of clothing.

[0065] In a specific embodiment, the type of clothing can be intelligently identified to determine the season suitable for wearing the clothing, thereby generating entries and pictures suitable for the season and adding them to the first reference sample and / or the second reference sample.

[0066] Specifically, the step of processing the first rendered image in step S200 includes identifying the range of clothing in the image and rendering the clothing in the image;

[0067] Among them, the recognition of the range of clothing in the image is conducive to helping the image generation algorithm to more accurately understand and imitate the shape, texture, color and other characteristics of clothing, and help the generation algorithm better restore the appearance and realism of clothing;

[0068] Rendering the clothing in an image helps make the image more realistic and closer to reality.

[0069] In this embodiment, a three-dimensional image containing clothing is used as a template mask to identify the range of the clothing to cooperate with the generation of the image in step S300. By identifying the range of the clothing in the template mask, the image generation algorithm can focus on the shape, part and specific detail information of the clothing, thereby producing a more detailed, realistic, accurate and stylized image.

[0070] Preferably, the clothing in the image is rendered using a rendering algorithm based on a VRay renderer to perform offline rendering of the clothing.

[0071] It should be noted that VRay renderer is a high-performance rendering engine for 3D graphics rendering, developed by Chaos Group, a Bulgaria company. It is widely used in movies, television, advertising, architecture, games and other fields, and can create impressive high-quality rendering effects. The advantages of VRay renderer are:

[0072] (1) High-quality image rendering: VRay uses physically based rendering technology to generate high-quality realistic images;

[0073] (2) Fast rendering speed: VRay is an optimized rendering engine that can generate high-quality images in a short time;

[0074] (3) Flexible rendering options: VRay provides many flexible rendering options, including a variety of light sources, shadows, reflections, refractions, depth of field and other special effects, allowing users to adjust as needed;

[0075] (4) Ability to integrate with commonly used 3D production software: VRay supports a variety of popular 3D production software, such as 3ds Max, Maya, SketchUp, etc., and can be integrated with them conveniently and quickly.

[0076] It should also be noted that offline rendering refers to rendering the 3D scene offline to generate imaging results, and then outputting the imaging results, while online rendering is to generate images or animations of the 3D scene in real time on the computer. The advantages of offline rendering over online rendering include:

[0077] (1) By improving the image's fineness and pixel quality, the image quality and realism are improved;

[0078] (2) Ability to handle more complex scenes: Since offline rendering can wait for calculation results when there is sufficient computing time, it can render very complex scenes containing a large number of objects and effects;

[0079] (3) More flexible timing: Offline rendering time depends on the speed of the computer and the complexity of the scene, but it is usually possible to pre-set the rendering time or perform post-processing after the calculation is completed. This means that offline rendering can arrange computing time and computing resources according to demand;

[0080] (4) Can be completed offline: Offline rendering can be run offline after the calculation is completed, while online rendering needs to be connected to the network at all times and perform real-time calculations, which requires larger computing resources and is also more limited by network speed and bandwidth.

[0081] It should be noted that the order of the two steps of identifying the clothing range in the image and rendering the clothing in the image can be adjusted. Figure 2 Optionally, step 200 includes:

[0082] S210: Based on the three-dimensional picture containing the clothing, identifying the range of the clothing in the first rendered image to obtain a clothing identification map.

[0083] S220: Based on the three-dimensional image containing the clothing, offline rendering is performed on the clothing in the clothing identification image to obtain a processed image.

[0084] or, see Figure 3 , step 200 comprises:

[0085] S230: Based on the three-dimensional picture containing the clothing, offline rendering is performed on the clothing in the first rendering image to obtain a second rendering image;

[0086] S240: Based on the three-dimensional picture containing the clothing, identifying the range of the clothing in the second rendered image to obtain a processed image.

[0087] It should be noted that rendering the clothing in the image first and then identifying the clothing range in the image can better achieve processing of detail parts.

[0088] For example, if the range of clothing in the image is first identified and then the clothing in the image is rendered, it is easy to fail to identify the fur in the furry clothing. However, if the clothing in the image is rendered first and then the range of clothing in the image is identified, the fur in the furry clothing can be correctly identified.

[0089] Preferably, step S300 generates a clothing picture with a human model of a specified effect based on the AIGC algorithm of stable diffusion. The user can generate several pictures through step S300 and select the pictures that meet the user's standards as the output results.

[0090] It should be noted that the AIGC (Artificial Intelligence Generated Content) algorithm based on stable diffusion is a deep learning algorithm for image generation. The algorithm adopts the concept of stable diffusion, combines image processing and artistic creation, and can generate high-quality realistic images.

[0091] The AIGC algorithm can generate high-resolution, realistic digital images. Its applications include creative arts, digital entertainment, visual effects, and high-quality CGI generation. In this algorithm, stable diffusion is applied to deep convolutional neural networks to generate high-quality, realistic images. By performing stable diffusion on the image, a high degree of detail retention and texture expression can be achieved.

[0092] Example 2

[0093] This embodiment proposes a device for generating a picture of a mannequin with clothing of a specified effect, see Figure 4 , the device comprises:

[0094] The rendering module 21 is used to take the three-dimensional picture containing the clothing and the three-dimensional picture of the digital mannequin wearing the clothing as input, and render the three-dimensional picture of the digital mannequin wearing the clothing according to the effect specified by the user to obtain a first rendered image;

[0095] A processing module 22, configured to process the first rendered image based on the three-dimensional image containing the clothing to obtain a processed image;

[0096] The generating module 23 is used to generate a plurality of clothing pictures with human models of specified effects based on the processed images.

[0097] The generation module 23 generates clothing pictures with human models of specified effects based on the stable diffusion AIGC algorithm. The user can generate several pictures through the generation module 23 and select the pictures that meet the user's standards as output results.

[0098] Specifically, the rendering module 21 includes:

[0099] The first rendering unit 211 is used to render the model in the three-dimensional picture of the digital human model wearing the clothing based on the effect in the first reference sample specified by the user;

[0100] The second rendering unit 212 is used to render the background in the three-dimensional picture of the digital human model wearing the clothing based on the effect in the second reference sample specified by the user.

[0101] Optionally, the first reference sample includes a model reference picture and / or a model style entry, and the second reference sample includes a background reference picture and / or a background style entry.

[0102] Preferably, the first reference sample and the second reference sample are generated based on a three-dimensional image containing clothing, pre-set or input by the user. The first reference sample and the second reference sample may contain multiple images and / or entries for the user to use, and the user can select several of the images and / or entries as the basis for rendering the model and background in the image.

[0103] It should be noted that the generation of the first reference sample and the second reference sample based on the three-dimensional image containing clothing is specifically achieved through the recognition of clothing.

[0104] In a specific embodiment, the type of clothing can be intelligently identified to determine the season suitable for wearing the clothing, thereby generating entries and pictures suitable for the season and adding them to the first reference sample and / or the second reference sample.

[0105] Specifically, the processing module 22 includes:

[0106] A third rendering unit 221 is used to perform offline rendering on the image based on the three-dimensional picture containing the clothing;

[0107] The recognition unit 222 is used to recognize the range of clothing in the image based on the three-dimensional picture containing the clothing.

[0108] The third rendering unit 221 renders the clothing in the image, which helps to make the image more realistic and close to reality;

[0109] The recognition unit 222 recognizes the range of clothing in the image, which helps the image generation algorithm to more accurately understand and imitate the shape, texture, color and other characteristics of the clothing, and helps the generation algorithm to better restore the appearance and realism of the clothing.

[0110] It should be noted that the order in which the third rendering unit 221 and the recognition unit 222 process the image can be adjusted. The clothing in the image is first rendered by the third rendering unit 221, and then the clothing range in the image is recognized by the recognition unit 222, which can better realize the processing of the details.

[0111] For example, if the range of clothing in the image is first identified by the recognition unit 222 and then the clothing in the image is rendered by the third rendering unit 221, it is easy to fail to identify the fur in the furry clothing. However, if the clothing in the image is first rendered by the third rendering unit 221 and then the range of clothing in the image is identified by the recognition unit 222, the fur in the furry clothing can be correctly identified.

[0112] In summary, the present invention provides a method and device for generating pictures of clothing with human models of specified effects. The scheme proposed in the present invention can render pictures according to the effects specified by the user. The personalized needs of the user are fully considered during the generation process, so that the generated pictures are more in line with the user's ideas. Compared with the traditional template generation method, it is more flexible and free. At the same time, a rendering method based on three-dimensional pictures is adopted, so that the generated pictures are more realistic and have better texture.

[0113] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a specified effect of a human model clothing picture, characterized in that: The method comprises: Taking the three-dimensional picture containing the clothing and the three-dimensional picture of the digital human model wearing the clothing as input, rendering the three-dimensional picture of the digital human model wearing the clothing according to the effect specified by the user to obtain a first rendered image; Based on the three-dimensional picture including the clothing, processing the first rendered image to obtain a processed image; Based on the processed image, a plurality of pictures of the clothing with human models having a specified effect are generated.

2. The method for generating a specified effect of a human model clothing picture according to claim 1, characterized in that: The rendering of the three-dimensional picture of the digital human model wearing the clothing according to the specified effect includes: Rendering the model in the three-dimensional picture of the digital human model wearing the clothing based on the effect in the first reference sample specified by the user; Based on the effect in the second reference sample specified by the user, the background in the three-dimensional picture of the digital human model wearing the clothing is rendered.

3. The method for generating a specified effect of a human model clothing picture according to claim 2, characterized in that: The first reference sample includes a model reference picture and / or a model style entry, and the second reference sample includes a background reference picture and / or a background style entry.

4. The method for generating a specified effect of a human model clothing picture according to claim 2 or 3, characterized in that: The first reference sample and the second reference sample are generated based on a three-dimensional image containing the clothing, are preset, or are input by the user.

5. The method for generating a specified effect of a human model clothing picture according to claim 1, characterized in that: The processing of the first rendered image based on the three-dimensional picture containing the clothing to obtain a processed image includes: Based on the three-dimensional picture containing the clothing, identifying the range of the clothing in the first rendering image to obtain a clothing identification map; Based on the three-dimensional picture containing the clothing, the clothing in the clothing identification image is rendered offline to obtain a processed image.

6. The method for generating a specified effect of a human model clothing picture according to claim 1, characterized in that: The processing of the first rendered image based on the three-dimensional picture containing the clothing to obtain a processed image includes: Based on the three-dimensional picture containing the clothing, offline rendering is performed on the clothing in the first rendering image to obtain a second rendering image; Based on the three-dimensional picture containing the clothing, the range of the clothing in the second rendered image is identified to obtain the processed image.

7. The method for generating a specified effect of a human model clothing picture according to claim 1, characterized in that: The clothing picture with the human model of the specified effect is generated based on the stable diffusion AIGC algorithm.

8. A device for generating a picture of a mannequin with clothing of a specified effect, characterized in that: The device comprises: a rendering module, for taking the three-dimensional picture containing the clothing and the three-dimensional picture of the digital human model wearing the clothing as input, and rendering the three-dimensional picture of the digital human model wearing the clothing according to the effect specified by the user to obtain a first rendered image; a processing module, configured to process the first rendered image based on the three-dimensional picture containing the garment to obtain a processed image; A generation module is used to generate a plurality of clothing pictures with human models of specified effects based on the processed images.

9. The device for generating a specified effect picture with a human model and clothing according to claim 8, characterized in that: The rendering module includes: A first rendering unit, configured to render a model in a three-dimensional picture of a digital human model wearing the clothing based on an effect in the first reference sample specified by the user; The second rendering unit is used to render the background in the three-dimensional picture of the digital human model wearing the clothing based on the effect in the second reference sample specified by the user.

10. The device for generating a specified effect of a human model clothing picture according to claim 8, characterized in that: The processing module comprises: A third rendering unit, configured to perform offline rendering on an image based on the three-dimensional picture containing the garment; The recognition unit is used to recognize the range of the clothing in the image based on the three-dimensional picture containing the clothing.

Images