Clothing display method, device, electronic device and storage medium

Abstract

The embodiment of the present invention discloses a clothing display method, device, electronic device and storage medium, the clothing display method comprising: cutting out the inner image of the clothing from the original clothing image of the clothing to be displayed to obtain a target clothing image; determining multiple clothing feature points from the target clothing image, and determining the model vertex corresponding to each clothing feature point in the multiple clothing feature points, the model vertex is the vertex of a three-dimensional model model; determining the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point; rendering the target clothing image to a three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model. The embodiment of the present invention can solve the body occlusion problem during clothing display, improve the display effect, and reduce the modeling cost.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer technology, and in particular to a clothing display method, device, electronic equipment and storage medium. Background Art

[0002] With the development of e-commerce, online clothing sales have also grown rapidly. When selling clothing online, you can use virtual fitting technology to display clothing. Existing virtual fitting technologies mainly include two-dimensional virtual fitting and three-dimensional virtual fitting. Two-dimensional virtual fitting mainly deforms the two-dimensional clothing image to fit the model's body posture, and then overlays the deformed image on the human model to achieve the try-on effect display; three-dimensional virtual fitting mainly performs three-dimensional modeling of clothing, and uses computer graphics technology to render the image of the person wearing the three-dimensional clothing on a three-dimensional model with an adjustable body shape, thereby achieving the try-on effect display.

[0003] In the process of realizing the present invention, the inventors found that two-dimensional virtual fitting adapts to the model's body posture through clothing deformation, but cannot process the semantic information of the clothing itself, that is, it cannot process the clothing area blocked by the body, and there is a problem of poor display effect; although three-dimensional virtual fitting can improve the display effect to a certain extent, it requires modeling of each piece of clothing, and there is a problem of high modeling cost. Summary of the invention

[0004] The embodiments of the present invention provide a clothing display method, device, electronic device and storage medium, which can solve the problem of body occlusion during clothing display, improve display effect and reduce modeling cost.

[0005] In a first aspect, an embodiment of the present invention provides a clothing display method, comprising:

[0006] The inner side image of the clothing is cut out from the original clothing image of the clothing to be displayed to obtain the target clothing image;

[0007] Determine a plurality of clothing feature points from the target clothing image, and determine a model vertex corresponding to each of the plurality of clothing feature points, wherein the model vertex is a vertex of a three-dimensional model model;

[0008] Determine the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point;

[0009] The target clothing image is rendered to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model.

[0010] In a second aspect, an embodiment of the present invention provides a clothing display device, the device comprising:

[0011] A cropping module is used to crop the inner side image of the clothing from the original clothing image of the clothing to be displayed to obtain a target clothing image;

[0012] A first determination module is used to determine a plurality of clothing feature points from the target clothing image, and determine a model vertex corresponding to each of the plurality of clothing feature points, wherein the model vertex is a vertex of a three-dimensional model model;

[0013] A second determination module is used to determine the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point;

[0014] A rendering module is used to render the target clothing image to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a clothing display method as described in any one of the embodiments of the present invention is implemented.

[0016] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a clothing display method as described in any one of the embodiments of the present invention.

[0017] In the embodiment of the present invention, the inner image of the clothing to be displayed can be cut out from the original clothing image of the clothing to be displayed to obtain the target clothing image; multiple clothing feature points are determined from the target clothing image, and the model vertices corresponding to each clothing feature point in the multiple clothing feature points are determined, and the model vertices are vertices of the three-dimensional model model; the texture mapping coordinates of each model vertex are determined according to the model vertex corresponding to each clothing feature point; the target clothing image is rendered to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model. Since the inner image of the clothing in the original clothing image should be an image blocked by the body, the problem of clothing being blocked by the body can be solved by rendering the target clothing image obtained by cutting out the inner image of the clothing to the three-dimensional model model; in addition, the target clothing image is rendered to the three-dimensional model model for display according to the texture mapping coordinates, and the two-dimensional image is displayed through the three-dimensional model, and the display effect is more real and natural, which improves the display effect; further, for the clothing to be displayed, it is only necessary to obtain the original clothing image and determine the clothing feature points, and it is not necessary to perform three-dimensional modeling for each piece of clothing to be displayed, thereby reducing the modeling cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a flow chart of the clothing display method provided by an embodiment of the present invention.

[0020] Figure 2 2 is another flow chart of the clothing display method provided by an embodiment of the present invention.

[0021] Figure 3a to Figure 3f Some schematic diagrams of display effects provided by embodiments of the present invention.

[0022] Figure 4 The figure is a structural schematic diagram of a clothing display device provided by an embodiment of the present invention.

[0023] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] Figure 1 The present invention provides a flow chart of a clothing display method according to an embodiment of the present invention. The method can be performed by a clothing display device according to an embodiment of the present invention. The device can be implemented in software and / or hardware. In a specific embodiment, the device can be integrated into an electronic device, such as a computer. The following embodiments will be described by taking the device integrated into an electronic device as an example. Figure 1 , the method may specifically include the following steps:

[0026] Step 101 , cutting out the inner side image of the garment from the original garment image to be displayed to obtain a target garment image.

[0027] For example, the clothing to be displayed may include shirts, jackets, T-shirts, pants, dresses, etc. The clothing to be displayed may be one piece of clothing or multiple pieces of clothing. When there are multiple pieces of clothing to be displayed, each piece of clothing to be displayed may correspond to an original clothing image, and the original clothing image may be an image obtained by photographing the clothing to be displayed.

[0028] Specifically, after obtaining the original clothing image of the clothing to be displayed, the original clothing image can be semantically segmented to segment the inside of the clothing, the outside of the clothing, the background, etc. in the original clothing image. Among them, the inside of the clothing is the inner surface of the clothing. When shooting the clothing to be displayed, part of the inner surface of the clothing (such as the back neckline, cuffs, the inside of the back skirt, etc.) may be exposed. Usually, when the model wears the clothing, the exposed part of the inner surface of the clothing should be blocked by the model and not visible; the outside of the clothing is the outer surface of the clothing. When the model wears the clothing, the outer surface should be visible. The outer surface is mainly used to show the appearance, style, material, color, etc. of the clothing; the background is the other parts of the image except the clothing to be displayed. This part may be blank, or it may be the scene or other objects that are in the picture when shooting the clothing to be displayed.

[0029] The original clothing image can be cropped according to the segmented inside of the clothing, outside of the clothing, and background. For example, the inside image of the clothing and the background image can be cropped from the original clothing image of the clothing to be displayed, thereby obtaining a target clothing image including the outside image of the clothing. When there are multiple pieces of clothing to be displayed, multiple target clothing images can be obtained. For example, when the clothing to be displayed includes a shirt and trousers, a target clothing image including the outside image of the shirt and a target clothing image including the outside image of the trousers can be obtained.

[0030] Step 102, determining a plurality of clothing feature points from the target clothing image, and determining a model vertex corresponding to each of the plurality of clothing feature points, where the model vertex is a vertex of the three-dimensional model model.

[0031] For example, the points corresponding to the human joints in the target clothing image can be determined, and a plurality of clothing feature points can be determined based on the points corresponding to the human joints in the target clothing image. For example, the points corresponding to the human joints in the target clothing image can be directly determined as clothing feature points, or some points can be selected from the points corresponding to the human joints in the target clothing image as clothing feature points. Among them, human joints include but are not limited to shoulder joints, elbow joints, vertebral joints, hip joints, knee joints, etc. When the type of clothing to be displayed (such as tops, pants) is different, the determined clothing feature points will also be different.

[0032] For example, the shape or outline of clothing in the target clothing image can also be detected, and multiple clothing feature points can be determined based on the clothing shape or outline. The specific number of clothing feature points can be set according to actual needs. For example, the clothing contour line in the target clothing image can be detected, and all or part of the points on the clothing contour line can be selected as clothing feature points. A clothing feature point can be a pixel point. When the type or style of the clothing to be displayed is different, the determined clothing feature points will also be different.

[0033] In a specific implementation, a three-dimensional model for displaying the clothing to be displayed can be pre-established, and after determining a plurality of clothing feature points from the target clothing image, the model vertex corresponding to each clothing feature point in the three-dimensional model model can be determined. Specifically, for example, the three-dimensional model model can be unfolded to a two-dimensional plane, a mapping relationship between points of the target clothing image and the two-dimensional plane can be established, and the model vertex corresponding to each clothing feature point can be determined according to the mapping relationship.

[0034] Step 103, determining the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point.

[0035] In the embodiment of the present invention, in order to distinguish from the three-dimensional coordinate system (expressed by X, Y, Z, where X represents the horizontal direction, Y represents the vertical direction, and Z represents the direction perpendicular to the XY plane), the two-dimensional coordinate system can be expressed by UV, where the horizontal direction is U, the vertical direction is V, and the texture mapping coordinates are UV coordinates. Specifically, the texture mapping coordinates of each clothing feature point can be determined first, and the texture mapping coordinates of each clothing feature point can be determined as the texture mapping coordinates of the corresponding model vertex. In addition, the gap position between points can be processed by software for image smoothing interpolation.

[0036] Step 104 , rendering the target clothing image to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model.

[0037] The specific rendering process can be understood as migrating the attribute information of the clothing feature points having the same texture mapping coordinates as the model vertices to the corresponding model vertices. The attribute information may include pixel values, lighting, shadows, brightness, etc. When there are multiple pieces of clothing to be displayed, the target clothing images corresponding to the multiple pieces of clothing to be displayed can be rendered to the 3D model so as to simultaneously display the multiple pieces of clothing to be displayed through the 3D model.

[0038] In the embodiment of the present invention, the inner image of the clothing to be displayed can be cut out from the original clothing image of the clothing to be displayed to obtain the target clothing image; multiple clothing feature points are determined from the target clothing image, and the model vertices corresponding to each clothing feature point in the multiple clothing feature points are determined, and the model vertices are vertices of the three-dimensional model model; the texture mapping coordinates of each model vertex are determined according to the model vertex corresponding to each clothing feature point; the target clothing image is rendered to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model. Since the inner image of the clothing in the original clothing image should be an image blocked by the body, the problem of clothing being blocked by the body can be solved by rendering the target clothing image obtained by cutting out the inner image of the clothing to the three-dimensional model model; in addition, the target clothing image is rendered to the three-dimensional model model for display according to the texture mapping coordinates, and the display effect is more real and natural, which improves the display effect; further, for the clothing to be displayed, it is only necessary to obtain the original clothing image and determine the clothing feature points, and it is not necessary to perform three-dimensional modeling for each piece of clothing to be displayed, thereby reducing the modeling cost.

[0039] The following examples further illustrate the clothing display method provided by the embodiment of the present invention. Figure 2 As shown, the clothing display method of the embodiment of the present invention may include the following steps:

[0040] Step 201 , semantic segmentation is performed on the original clothing image of the clothing to be displayed to obtain a mask image.

[0041] For example, the clothing to be displayed may include shirts, coats, T-shirts, pants, dresses, etc., and the original clothing image may be an image obtained by photographing the clothing to be displayed. Specifically, a semantic segmentation model may be used to perform semantic segmentation on the original clothing image of the clothing to be displayed to obtain a mask image, in which the category information of each pixel in the image is marked, and the category information includes the inside of the clothing, the outside of the clothing, and the background.

[0042] Step 202 , the inner side image of the clothing is cut out from the original clothing image according to the mask image, so as to obtain a target clothing image.

[0043] For example, the size of the mask image can be the same as the size of the original clothing image. The inner clothing area, outer clothing area and background area in the original clothing image can be determined based on the type information of each pixel in the mask image. The inner clothing image and the background image in the original clothing image are cropped according to the area division, thereby obtaining a target clothing image including the outer clothing image.

[0044] Step 203, determining the points corresponding to the human body joints in the target clothing image.

[0045] Step 204, determining a plurality of clothing feature points according to the points corresponding to the human body joints in the target clothing image.

[0046] For example, the points corresponding to the human joints in the target clothing image can be directly determined as clothing feature points, or some points can be selected from the points corresponding to the human joints in the target clothing image as clothing feature points. Among them, human joints include but are not limited to shoulder joints, elbow joints, vertebral joints, hip joints, knee joints, etc. When the type of clothing to be displayed (such as tops, pants) is different, the determined clothing feature points will also be different. A clothing feature point can be a pixel point, and the specific number of clothing feature points can be set according to actual needs.

[0047] Step 205 , normalizing the coordinates of each clothing feature point according to the width and height of the target clothing image to obtain the texture mapping coordinates of each clothing feature point.

[0048] Specifically, the U value in the coordinates of each clothing feature point may be divided by the image width value, and the V value may be divided by the image height value, so as to normalize the coordinates of each clothing feature point to facilitate subsequent calculations.

[0049] Step 206, obtaining the gender information of the clothing to be displayed.

[0050] For example, the gender information may be information used to indicate the gender of the person to whom the clothing to be displayed is suitable, and the gender information may be, for example, male, female, etc. Furthermore, in order to present a more accurate display effect, the gender information may also be: men, women, boys, girls, etc.

[0051] Step 207, obtaining a three-dimensional model according to the gender information.

[0052] For example, the 3D mannequin model can be obtained from a preset model library, which may include various models, such as a male mannequin model, a female mannequin model, a boy mannequin model, a girl mannequin model, etc. For example, if the gender information of the clothing to be displayed is a boy, a boy mannequin model can be obtained, and if the gender information of the clothing to be displayed is a woman, a woman mannequin model can be obtained.

[0053] Step 208, determining the model vertex corresponding to each clothing feature point, where the model vertex is the vertex of the three-dimensional model model.

[0054] Specifically, for example, the three-dimensional model can be unfolded to a two-dimensional plane, a mapping relationship between the target clothing image and the two-dimensional plane is established, and the model vertex corresponding to each clothing feature point is determined according to the mapping relationship.

[0055] Step 209: Determine the texture mapping coordinates of each clothing feature point as the texture mapping coordinates of the corresponding model vertex.

[0056] That is, the model vertex corresponding to each clothing feature point has not only the coordinates (X, Y, Z) of the three-dimensional coordinate system, but also the coordinates (U, V) of the two-dimensional coordinate system.

[0057] Step 210, determining the occlusion relationship of multiple pieces of clothing to be displayed.

[0058] When there are multiple garments to be displayed, the occlusion relationship of the multiple garments to be displayed can be determined. Specifically, the occlusion relationship of the multiple garments to be displayed can be determined according to preset data (i.e., preset occlusion relationship), or according to user input data obtained from a preset interface. The specific occlusion relationship can be, for example, a top occludes pants, a coat occludes a shirt and a T-shirt, etc.

[0059] Step 211, determining display information of overlapping areas of multiple garments to be displayed according to the occlusion relationship.

[0060] That is, determine which garment is displayed in the overlapping area of ​​multiple garments to be displayed. For example, when multiple garments to be displayed include a top and trousers, if the occlusion relationship is that the top occludes the trousers, then the display information of the overlapping area of ​​the top and the trousers can be determined to be the top; for another example, when multiple garments to be displayed include a shirt and a coat, if the occlusion relationship is that the coat occludes the shirt, then the display information of the overlapping area of ​​the shirt and the coat can be determined to be the coat.

[0061] Step 212 , rendering the target clothing image to the three-dimensional model model according to the display information of the overlapping area and the texture mapping coordinates of each model vertex, so as to display multiple pieces of clothing to be displayed through the three-dimensional model model.

[0062] The specific rendering process can be understood as migrating the attribute information of the clothing feature points having the same texture mapping coordinates as the model vertices to the corresponding model vertices. The attribute information may include pixel values, lighting, shadows, brightness, etc.

[0063] Specifically, when there are multiple garments to be displayed and there are overlapping areas between the multiple garments to be displayed, there may be multiple garment feature points whose texture mapping coordinates are the same as the texture mapping coordinates of a certain model vertex, and the attribute information of which garment feature point should be migrated to the corresponding model vertex can be determined based on the display information of the overlapping area. For example, if the multiple garments to be displayed include a top and trousers, and the display information of the overlapping area of ​​the top and the trousers is a top, the attribute information of the garment feature point corresponding to the top can be migrated to the corresponding model vertex.

[0064] When there are multiple garments to be displayed, the target garment images of the multiple garments to be displayed may be rendered to the 3D model at one time, or may be rendered to the 3D model multiple times.

[0065] In the embodiment of the present invention, the inner image of the clothing to be displayed can be cut out from the original clothing image of the clothing to be displayed to obtain the target clothing image; multiple clothing feature points are determined from the target clothing image, and the model vertices corresponding to each clothing feature point in the multiple clothing feature points are determined, and the model vertices are vertices of the three-dimensional model model; the texture mapping coordinates of each model vertex are determined according to the model vertex corresponding to each clothing feature point; the target clothing image is rendered to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model. Since the inner image of the clothing in the original clothing image should be an image blocked by the body, the problem of clothing being blocked by the body can be solved by rendering the target clothing image obtained by cutting out the inner image of the clothing to the three-dimensional model model; in addition, the target clothing image is rendered to the three-dimensional model model for display according to the texture mapping coordinates, and the display effect is more real and natural, which improves the display effect; further, for the clothing to be displayed, it is only necessary to obtain the original clothing image and determine the clothing feature points, and it is not necessary to perform three-dimensional modeling for each piece of clothing to be displayed, thereby reducing the modeling cost.

[0066] In addition, when there are multiple garments to be displayed, the display information of the overlapping area of ​​the garments can be determined according to the occlusion relationship, and the target garment image can be rendered according to the display information of the overlapping area of ​​the garments and the texture map coordinates of each model vertex, which solves the occlusion problem between garments and further improves the display effect of the garments. When displaying multiple garments, it is only necessary to obtain the image of each garment and determine the garment feature points. There is no need to pre-generate the matching effect between garments of different categories. It is highly controllable, facilitates the matching display of garments of different brands and categories, and expands the application scenarios of garment display.

[0067] The following takes women's tops as an example of the clothing to be displayed to illustrate the clothing display method provided by the embodiment of the present invention.

[0068] For example, the original clothing image of the clothing to be displayed is Figure 3a As shown in the figure, it is an image of a lady's top. Then the inner image of the clothing can be cut out from the original clothing image ( Figure 3a The back neckline in the middle) and the background image are obtained as follows Figure 3b The target clothing image shown in FIG. The multiple clothing feature points determined in the target clothing image can be as follows: Figure 3c As shown, the points corresponding to the human body joints in the target clothing image.

[0069] Since the original clothing image is a woman's top, a woman's model model can be obtained. The obtained woman's model model can be, for example, Figure 3dNext, determine the model vertex corresponding to each clothing feature point in the lady model, determine the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point, and map the target clothing image according to the texture mapping coordinates of each model vertex. Figure 3b Rendering to a female mannequin model Figure 3d , the rendering effect can be shown as Figure 3e shown.

[0070] Further, when it is also necessary to put the pants on the lady model Figure 3d When displaying on the screen, the occlusion relationship between the top and the pants can be determined: the top occludes the pants, that is, the top is displayed in the overlapping area of ​​the clothing, and then the target clothing image of the pants is rendered to the female model model. Figure 3d , the effect after rendering is like Figure 3f As shown, the use of the lady model is realized Figure 3d Show the effect of top and pants at the same time.

[0071] It should be noted that the renderings shown in the embodiments of the present disclosure are intended to illustrate the clothing display method of the embodiments of the present invention, and the content presented in the specific interface (including but not limited to feature points, pictures, expressions, etc.) does not constitute a limitation on the solution.

[0072] Figure 4 1 is a structural diagram of a clothing display device provided by an embodiment of the present invention, and the device is suitable for executing the clothing display method provided by an embodiment of the present invention. Figure 4 As shown, the device may specifically include:

[0073] A cutting module 401 is used to cut out the inner side image of the garment from the original garment image to be displayed to obtain a target garment image;

[0074] A first determining module 402 is used to determine a plurality of clothing feature points from the target clothing image, and determine a model vertex corresponding to each of the plurality of clothing feature points, wherein the model vertex is a vertex of a three-dimensional model model;

[0075] The second determination module 403 is used to determine the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point;

[0076] The rendering module 404 is used to render the target clothing image to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model.

[0077] In one embodiment, the trimming module 401 is specifically used for:

[0078] Performing semantic segmentation on the original clothing image to obtain a mask image, wherein the mask image is marked with category information of each pixel, and the category information includes the inside and the outside of the clothing;

[0079] The inner side image of the clothing is cut out from the original clothing image according to the mask image to obtain the target clothing image, wherein the target clothing image includes the outer side image of the clothing.

[0080] In one embodiment, the first determining module 402 determines a plurality of clothing feature points from the target clothing image, including:

[0081] Determine points corresponding to human body joints in the target clothing image;

[0082] The plurality of clothing feature points are determined according to points corresponding to the human body joints in the target clothing image.

[0083] In one embodiment, the device further comprises:

[0084] The normalization module is used to normalize the coordinates of each clothing feature point according to the width and height of the target clothing image to obtain the texture mapping coordinates of each clothing feature point.

[0085] In one embodiment, the second determining module 403 is specifically configured to:

[0086] The texture mapping coordinates of each clothing feature point are determined as the texture mapping coordinates of the corresponding model vertex.

[0087] In one embodiment, the clothing to be displayed includes multiple pieces, and the rendering module 404 is specifically used to:

[0088] Determining the occlusion relationship of the multiple pieces of clothing to be displayed;

[0089] Determining display information of overlapping areas of the plurality of garments to be displayed according to the occlusion relationship;

[0090] The target clothing image is rendered to the three-dimensional model model according to the display information of the overlapping area and the texture mapping coordinates of each model vertex, so as to display the multiple pieces of clothing to be displayed through the three-dimensional model model.

[0091] In one embodiment, the device further comprises:

[0092] The acquisition module is used to acquire the gender information of the clothing to be displayed; and acquire the three-dimensional model according to the gender information.

[0093] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0094] The device of the embodiment of the present invention can cut out the inner image of the clothing from the original clothing image of the clothing to be displayed to obtain the target clothing image; determine multiple clothing feature points from the target clothing image, and determine the model vertex corresponding to each clothing feature point in the multiple clothing feature points, the model vertex is the vertex of the three-dimensional model model; determine the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point; render the target clothing image to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model. Since the inner image of the clothing in the original clothing image should be an image blocked by the body, by rendering the target clothing image obtained by cutting out the inner image of the clothing to the three-dimensional model model, the problem of clothing being blocked by the body can be solved; in addition, the target clothing image is rendered to the three-dimensional model model for display according to the texture mapping coordinates, and the display effect is more real and natural, which improves the display effect; further, for the clothing to be displayed, it is only necessary to obtain the original clothing image and determine the clothing feature points, and it is not necessary to perform three-dimensional modeling for each piece of clothing to be displayed, thereby reducing the modeling cost.

[0095] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the clothing display method provided in any of the above embodiments is implemented.

[0096] An embodiment of the present invention further provides a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the clothing display method provided by any of the above embodiments is implemented.

[0097] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 of an electronic device suitable for implementing an embodiment of the present invention. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0098] like Figure 5As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0099] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0100] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present invention are executed.

[0101] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM 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 above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0102] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0103] The modules and / or units involved in the embodiments of the present invention may be implemented in software or hardware. The modules and / or units described may also be set in a processor, for example, it may be described as: a processor includes a clipping module, a first determination module, a second determination module and a rendering module. The names of these modules do not, in some cases, constitute limitations on the modules themselves.

[0104] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:

[0105] The inner image of the clothing is cropped from the original clothing image of the clothing to be displayed to obtain a target clothing image; a plurality of clothing feature points are determined from the target clothing image, and a model vertex corresponding to each of the plurality of clothing feature points is determined, wherein the model vertex is a vertex of a three-dimensional model model; the texture mapping coordinates of each model vertex are determined according to the model vertex corresponding to each clothing feature point; the target clothing image is rendered to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model.

[0106] According to the technical solution of the embodiment of the present invention, the inner image of the clothing to be displayed can be cut out from the original clothing image of the clothing to be displayed to obtain the target clothing image; multiple clothing feature points are determined from the target clothing image, and the model vertices corresponding to each clothing feature point in the multiple clothing feature points are determined, and the model vertices are the vertices of the three-dimensional model model; the texture mapping coordinates of each model vertex are determined according to the model vertex corresponding to each clothing feature point; the target clothing image is rendered to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model. Since the inner image of the clothing in the original clothing image should be an image blocked by the body, the problem of clothing being blocked by the body can be solved by rendering the target clothing image obtained by cutting out the inner image of the clothing to the three-dimensional model model; in addition, the target clothing image is rendered to the three-dimensional model model for display according to the texture mapping coordinates, and the display effect is more real and natural, which improves the display effect; further, for the clothing to be displayed, it is only necessary to obtain the original clothing image and determine the clothing feature points, and it is not necessary to perform three-dimensional modeling for each piece of clothing to be displayed, thereby reducing the modeling cost.

[0107] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A clothing display method, characterized in that: include: Clipping the inner side image of the clothing from the original clothing image of the clothing to be displayed to obtain the target clothing image, including: performing semantic segmentation on the original clothing image to obtain a mask image, wherein the category information of each pixel point is marked in the mask image, and the category information includes the inner side of the clothing and the outer side of the clothing; clipping the inner side image of the clothing from the original clothing image according to the mask image to obtain the target clothing image, wherein the target clothing image includes the outer side image of the clothing, wherein the inner side image of the clothing is an invisible image when the clothing to be displayed is displayed using a three-dimensional model model, and the outer side image of the clothing is a visible image when the clothing to be displayed is displayed using a three-dimensional model model; Determine a plurality of clothing feature points from the target clothing image, and determine a model vertex corresponding to each of the plurality of clothing feature points, wherein the model vertex is a vertex of a three-dimensional model model; Determine the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point; The target clothing image is rendered to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model.

2. The clothing display method according to claim 1, characterized in that: Determining a plurality of clothing feature points from the target clothing image comprises: Determine points corresponding to human body joints in the target clothing image; The plurality of clothing feature points are determined according to points corresponding to the human body joints in the target clothing image.

3. The clothing display method according to claim 1, characterized in that: After determining a plurality of clothing feature points from the target clothing image, the method further includes: The coordinates of each clothing feature point are normalized according to the width and height of the target clothing image to obtain the texture mapping coordinates of each clothing feature point.

4. The clothing display method according to claim 3, characterized in that: The step of determining the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point comprises: The texture mapping coordinates of each clothing feature point are determined as the texture mapping coordinates of the corresponding model vertex.

5. The clothing display method according to any one of claims 1 to 4, characterized in that: The garments to be displayed include a plurality of pieces, and the step of rendering the target garment image to the three-dimensional model model according to the texture mapping coordinates of each vertex of the model so as to display the garments to be displayed through the three-dimensional model model comprises: Determining the occlusion relationship of the multiple pieces of clothing to be displayed; Determining display information of overlapping areas of the plurality of garments to be displayed according to the occlusion relationship; The target clothing image is rendered to the three-dimensional model model according to the display information of the overlapping area and the texture mapping coordinates of each model vertex, so as to display the multiple pieces of clothing to be displayed through the three-dimensional model model.

6. The clothing display method according to any one of claims 1 to 4, characterized in that: Before determining the model vertex corresponding to each clothing feature point in the plurality of clothing feature points, the method further includes: Obtaining gender information of the clothing to be displayed; The three-dimensional model is obtained according to the gender information.

7. A clothing display device, characterized in that: include: The cropping module is used to crop the inner side image of the clothing from the original clothing image of the clothing to be displayed to obtain the target clothing image, including: performing semantic segmentation on the original clothing image to obtain a mask image, wherein the category information of each pixel point is marked in the mask image, and the category information includes the inner side of the clothing and the outer side of the clothing; cropping the inner side image of the clothing from the original clothing image according to the mask image to obtain the target clothing image, wherein the target clothing image includes the outer side image of the clothing, wherein the inner side image of the clothing is an invisible image when the clothing to be displayed is displayed using a three-dimensional model model, and the outer side image of the clothing is a visible image when the clothing to be displayed is displayed using a three-dimensional model model; A first determination module is used to determine a plurality of clothing feature points from the target clothing image, and determine a model vertex corresponding to each of the plurality of clothing feature points, wherein the model vertex is a vertex of a three-dimensional model model; A second determination module is used to determine the texture mapping coordinates of each model vertex according to the model vertex corresponding to each clothing feature point; A rendering module is used to render the target clothing image to the three-dimensional model model according to the texture mapping coordinates of each model vertex, so as to display the clothing to be displayed through the three-dimensional model model.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the clothing display method as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the clothing display method as described in any one of claims 1 to 6 is implemented.

Images