Garment try-on method and apparatus, and computing device cluster

Abstract

Embodiments of the present application provide a garment try-on method and apparatus, and a computing device cluster. The garment try-on method comprises: acquiring at least one image of a real garment; performing matching retrieval in a plurality of virtual garment models on the basis of the at least one image of the real garment to acquire a retrieval result, and obtaining a garment try-on model on the basis of the retrieval result; acquiring a virtual human body model; combining the virtual human body model and the garment try-on model to obtain a virtual wearing model, the virtual wearing model being a model of a virtual human body wearing a virtual garment; and performing image rendering on the basis of the virtual wearing model, to generate a virtual human image wearing the virtual garment. In the garment try-on method according to the embodiments of the present application, a real garment can be identified to achieve try-on of a virtual garment corresponding to the real garment, thereby simplifying a virtual garment try-on process, and improving a user's experience of trying on the virtual garment.

Description

Clothing fitting method, device and computing device cluster

[0001] The present application claims priority to the Chinese patent application No. 202411375279.1, filed on September 29, 2024, and entitled "Clothing fitting method, device and computing device cluster", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the technical field of computer, and in particular, to a clothing fitting method, device and computing device cluster. BACKGROUND

[0003] With the continuous improvement of living standards, people purchase clothes, shoes and hats and the like more frequently, and the inconvenience of trying on and wearing has become one of the bottlenecks restricting consumption. Therefore, a clothing fitting method applied to a computing device is needed to assist users in trying on and wearing clothes, shoes and hats and the like, so as to improve the convenience of trying on and wearing. SUMMARY

[0004] In order to solve the problem of how to assist users in trying on and wearing clothes, shoes and hats and the like, the present application provides a clothing fitting method, device and computing device cluster, and further provides a computer readable storage medium.

[0005] The embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, the present application provides a clothing fitting method, comprising:

[0007] obtaining at least one image of a real clothing;

[0008] performing matching retrieval in a plurality of virtual clothing models according to the at least one image of the real clothing, obtaining a retrieval result, and obtaining a fitting clothing model according to the retrieval result;

[0009] obtaining a virtual human model;

[0010] combining the virtual human model and the fitting clothing model to obtain a virtual wearing model, the virtual wearing model being a model of a virtual human wearing virtual clothing;

[0011] performing image rendering based on the virtual wearing model to generate a virtual character image wearing virtual clothing.

[0012] According to the method of the first aspect, the fitting and wearing of virtual clothing corresponding to the real clothing can be realized by identifying the real clothing, which simplifies the process of virtual clothing fitting and wearing and improves the user experience of virtual clothing fitting and wearing.

[0013] In an implementation form of the first aspect, the obtaining the try-on clothes model according to the at least one image of the real clothes and the searching in the plurality of virtual clothes models comprises:

[0014] searching one or more first virtual clothes models from the plurality of virtual clothes models, wherein the one or more first virtual clothes models have a matching degree with the at least one image of the real clothes exceeding a first preset value;

[0015] obtaining the try-on clothes model according to the one or more first virtual clothes models.

[0016] According to the method in the above implementation form, the virtual clothes corresponding to the real clothes is searched based on the preset matching degree threshold, so that the user can avoid manually searching for the virtual clothes from the plurality of virtual clothes, and the user operation is simplified.

[0017] In an implementation form of the first aspect, the searching one or more first virtual clothes models from the plurality of virtual clothes models comprises:

[0018] inputting the at least one image of the real clothes into a neural network model to obtain the one or more first virtual clothes models.

[0019] According to the method in the above implementation form, the neural network model is used to search the virtual clothes model, so that the difficulty of searching the virtual clothes model is reduced, and the reliability of searching the virtual clothes model is improved.

[0020] In an implementation form of the first aspect, the obtaining the try-on clothes model according to the one or more first virtual clothes models comprises:

[0021] selecting one of the one or more first virtual clothes models having the highest matching degree with the at least one image of the real clothes as the try-on clothes model.

[0022] In an implementation form of the first aspect, the obtaining the try-on clothes model according to the one or more first virtual clothes models comprises:

[0023] providing a virtual clothes selection page, wherein the virtual clothes selection page is used to display one or more virtual clothes images corresponding to each of the one or more first virtual clothes models;

[0024] receiving a selection instruction of a user, wherein the selection instruction is used to indicate a virtual clothes image selected by the user from the one or more virtual clothes images;

[0025] The first virtual clothing model corresponding to the virtual clothing image selected by the user is taken as the try-on clothing model.

[0026] According to the method of the above implementation manner, under the premise of searching for the virtual clothing corresponding to the real clothing by matching degree, the final confirmation is made by the user, the accuracy of the real clothing recognition result is improved, and the user experience of virtual clothing try-on and try-wearing is improved.

[0027] In an implementation manner of the first aspect, the searching for the try-on clothing model from the plurality of virtual clothing models according to the image of the at least one real clothing further includes:

[0028] When the one or more first virtual clothing models are not searched, searching for one or more second virtual clothing models from the plurality of virtual clothing models, which have a clothing style matching degree with the image of the at least one real clothing exceeding a second preset value, and searching for one or more third virtual clothing models from the plurality of virtual clothing models, which have a clothing color matching degree with the image of the at least one real clothing exceeding a third preset value;

[0029] generating one or more fourth virtual clothing models according to the one or more second virtual clothing models and the one or more third virtual clothing models, wherein the clothing style of the one or more fourth virtual clothing models matches the one or more second virtual clothing models, and the clothing color of the one or more fourth virtual clothing models matches the one or more third virtual clothing models;

[0030] obtaining the try-on clothing model according to the one or more fourth virtual clothing models.

[0031] According to the method of the above implementation manner, in the case that the virtual clothing corresponding to the real clothing cannot be searched by matching degree, the virtual clothing corresponding to the real clothing is obtained by combining the clothing style and the color of the existing virtual clothing, the accuracy of the real clothing recognition result is improved, the success rate of obtaining the virtual clothing corresponding to the real clothing is improved, and the user experience of virtual clothing try-on and try-wearing is improved.

[0032] In an implementation manner of the first aspect, the combining the virtual human body model and the try-on clothing model to obtain a virtual wearing model includes:

[0033] obtaining a virtual clothing model matched with the try-on clothing model from the plurality of virtual clothing models;

[0034] combining the virtual human body model, the try-on clothing model, and the virtual clothing model matched with the try-on clothing model to obtain the virtual wearing model.

[0035] In an implementation form of the first aspect, the obtaining, from the plurality of virtual clothes models, a virtual clothes model matched with the try-on clothes model comprises:

[0036] obtaining clothes features corresponding to the try-on clothes model, the clothes features comprising clothes type and / or clothes color;

[0037] determining clothes features matched with the try-on clothes model according to the clothes features corresponding to the try-on clothes model;

[0038] obtaining a virtual clothes model matched with the try-on clothes model based on the clothes features matched with the try-on clothes model.

[0039] According to the method in the above implementation form, the virtual clothes model matched with the try-on clothes model is obtained, the try-on clothes model and the virtual clothes model matched with the try-on clothes model are both worn on the virtual human body model, and the virtual character image wearing the full set of virtual clothes is displayed to the user, which optimizes the virtual clothes try-on effect of the virtual character image, improves the visual effect of the virtual character image, and improves the user experience of the virtual clothes try-on and wearing.

[0040] In an implementation form of the first aspect, the method further comprises:

[0041] configuring a body action of the virtual character image, and / or configuring a display scene of the virtual character image.

[0042] In an implementation form of the first aspect:

[0043] the combining the virtual human body model and the try-on clothes model to obtain a virtual wearing model comprises: performing a first simulation process according to the virtual human body model and the try-on clothes model to generate the virtual wearing model;

[0044] the configuring the body action of the virtual character image, and / or the configuring the display scene of the virtual character image comprises: performing a second simulation process according to the configuration information of the body action and / or the configuration information of the display scene and the virtual wearing model.

[0045] According to the method in the above implementation form, in the case of not replacing the try-on clothes and only adjusting the body action and / or the display scene, it is not necessary to perform the first simulation process for the try-on clothes model again, but only to perform the second simulation process again, thereby reducing the simulation calculation amount.

[0046] In a second aspect, the present application provides a clothes try-on device, the device comprising:

[0047] an image acquisition module, configured to acquire at least one image of a real garment;

[0048] a virtual garment matching module, configured to perform matching search in a plurality of virtual garment models according to the at least one image of the real garment, acquire a search result, and obtain a try-on garment model according to the search result;

[0049] a virtual human structure module, configured to acquire a virtual human model;

[0050] a try-on module, configured to combine the virtual human model and the try-on garment model to obtain a virtual wearing model, the virtual wearing model being a model of a virtual human wearing a virtual garment;

[0051] a display module, configured to perform image rendering based on the virtual wearing model to generate a virtual character image wearing a virtual garment.

[0052] According to the device of the second aspect, the try-on and try-wearing of the virtual garment corresponding to the real garment can be realized by recognizing the real garment, the process of the virtual garment try-on and try-wearing is simplified, and the user experience of the virtual garment try-on and try-wearing is improved.

[0053] In an implementation form of the second aspect, the virtual garment matching module is configured to:

[0054] search, in the plurality of virtual garment models, one or more first virtual garment models having a matching degree with the at least one image of the real garment exceeding a first preset value;

[0055] obtain the try-on garment model according to the one or more first virtual garment models.

[0056] In an implementation form of the second aspect, the virtual garment matching module is configured to:

[0057] input the at least one image of the real garment into a neural network model to obtain the one or more first virtual garment models.

[0058] In an implementation form of the second aspect, the virtual garment matching module is configured to:

[0059] take one of the one or more first virtual garment models having the highest matching degree with the at least one image of the real garment as the try-on garment model.

[0060] In an implementation form of the second aspect:

[0061] The display module is configured to provide a virtual clothes selection page for displaying one or more virtual clothes images respectively corresponding to the one or more first virtual clothes models.

[0062] The virtual clothes matching module is configured to:

[0063] receive a selection instruction of a user, the selection instruction being used to indicate a virtual clothes image selected by the user from the one or more virtual clothes images;

[0064] take the first virtual clothes model corresponding to the virtual clothes image selected by the user as the try-on clothes model.

[0065] In an implementation form of the second aspect, the virtual clothes matching module is further configured to:

[0066] when the one or more first virtual clothes models are not retrieved, retrieve, from the plurality of virtual clothes models, one or more second virtual clothes models having a clothes style matching degree with the at least one real clothes image exceeding a second preset value, and retrieve one or more third virtual clothes models having a clothes color matching degree with the at least one real clothes image exceeding a third preset value;

[0067] generate one or more fourth virtual clothes models according to the one or more second virtual clothes models and the one or more third virtual clothes models, wherein the one or more fourth virtual clothes models have a clothes style matching the one or more second virtual clothes models, and the one or more fourth virtual clothes models have a clothes color matching the one or more third virtual clothes models;

[0068] obtain the try-on clothes model according to the one or more fourth virtual clothes models.

[0069] In an implementation form of the second aspect, the try-on module is configured to:

[0070] obtain, from the plurality of virtual clothes models, a virtual clothes model matched with the try-on clothes model;

[0071] combine the virtual human body model, the try-on clothes model, and the virtual clothes model matched with the try-on clothes model to obtain the virtual wearing model.

[0072] In an implementation form of the second aspect, the try-on module is configured to:

[0073] obtain a clothes feature corresponding to the try-on clothes model, the clothes feature including a clothes type and / or a clothes color;

[0074] determine, according to the clothing characteristics corresponding to the try-on clothing model, clothing characteristics matched with the try-on clothing model;

[0075] obtain a virtual clothing model matched with the try-on clothing model based on the clothing characteristics matched with the try-on clothing model.

[0076] In an implementation form of the second aspect, the display module is further configured to:

[0077] configure a body action of the virtual character image, and / or configure a display scene of the virtual character image.

[0078] In an implementation form of the second aspect:

[0079] The try-on module is configured to perform a first simulation process according to the virtual human model and the try-on clothing model, to generate the virtual wearing model.

[0080] The display module is further configured to perform a second simulation process according to the configuration information of the body action and / or the configuration information of the display scene, and the virtual wearing model.

[0081] In a third aspect, the present application provides a computing device cluster, comprising at least one computing device, each computing device comprising a memory and a processor;

[0082] The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster performs the method of the first aspect.

[0083] In a fourth aspect, the present application provides a computer program product comprising instructions which, when executed by a computing device system, cause a computing device cluster to perform the method of the first aspect.

[0084] In a fifth aspect, the present application provides a computer-readable storage medium comprising computer program instructions which, when executed by a computing device cluster, cause the computing device cluster to perform the method of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0085] Fig. 1 is a schematic diagram of a virtual clothing wearing process according to an embodiment of the present application;

[0086] Fig. 2 is a schematic diagram of a clothing try-on device structure according to an embodiment of the present application;

[0087] Fig. 3 is a flowchart of a clothing try-on method according to an embodiment of the present application;

[0088] Fig. 4 is a partial flowchart of a clothing try-on method according to an embodiment of the present application;

[0089] Figure 5 is a partial flow chart of a clothes fitting method according to an embodiment of the present application;

[0090] Figure 6 is a partial flow chart of a clothes fitting method according to an embodiment of the present application;

[0091] Figure 7 is a partial flow chart of a clothes fitting method according to an embodiment of the present application;

[0092] Figure 8 is a flow chart of a clothes fitting method according to an embodiment of the present application;

[0093] Figure 9 is a flow chart of a clothes fitting method according to an embodiment of the present application;

[0094] Figure 10 is a schematic diagram of a mobile phone screen display interface according to an embodiment of the present application;

[0095] Figure 11 is a schematic diagram of a mobile phone screen display interface according to an embodiment of the present application;

[0096] Figure 12 is a schematic diagram of a mobile phone screen display interface according to an embodiment of the present application;

[0097] Figure 13 is a flow chart of a clothes fitting method according to an embodiment of the present application;

[0098] Figure 14 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application;

[0099] Figure 15 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application;

[0100] Figure 16 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application;

[0101] Figure 17 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application;

[0102] Figure 18 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application;

[0103] Figure 19 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application;

[0104] Figure 20 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application;

[0105] Figure 21 is a flow chart of a clothes fitting method according to an embodiment of the present application;

[0106] Figure 22 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application;

[0107] Figure 23 is a flow chart of a clothes fitting method according to an embodiment of the present application;

[0108] FIG. 24 is a schematic diagram of a computing device structure according to an embodiment of the present application;

[0109] FIG. 25 is a schematic diagram of a computing device cluster according to an embodiment of the present application;

[0110] FIG. 26 is a schematic diagram of a computing device cluster network connection according to an embodiment of the present application. DETAILED DESCRIPTION

[0111] For the purposes of the present application, the technical solutions and advantages will be more clearly apparent from the following description of embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of the present application.

[0112] The terms used in the embodiments of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0113] For the problem of how to help users try on and wear clothes, shoes, hats and other articles, a feasible technical solution is to show the wearing effect of real clothes corresponding to virtual clothes to the user by wearing virtual clothes on a 3D virtual human model.

[0114] FIG. 1 is a schematic diagram of a virtual clothes wearing process according to an embodiment of the present application.

[0115] The computing device performs the following process shown in FIG. 1 to realize the wearing effect display of virtual clothes.

[0116] S100, obtaining a virtual clothes model of a virtual clothes selected by a user.

[0117] For example, in an embodiment, the display screen of the computing device displays a virtual clothes list, and the user selects a virtual clothes for which the wearing effect needs to be displayed from the virtual clothes list through touch or gesture. Based on the selection operation of the user, the virtual clothes model of the virtual clothes selected by the user is obtained.

[0118] S101, obtaining a virtual human model for 3D human modeling.

[0119] S102, combining the virtual clothes model and the virtual human model to obtain a virtual wearing model, which is a model of a virtual human wearing virtual clothes.

[0120] S103, performing image rendering based on the virtual wearing model, and displaying a virtual human image corresponding to the virtual wearing model.

[0121] Based on the above process, the user can be shown the wearing effect of the real clothes corresponding to the virtual clothes by showing the user a 3D virtual person image wearing the virtual clothes.

[0122] However, the implementation of the above process requires the user to select the virtual clothes that the user wants to try on from a plurality of virtual clothes in a virtual clothes list. The association between the virtual clothes in the virtual clothes list and the real clothes in reality is usually only reflected in appearance, i.e., the user needs to visually identify the correspondence between the real clothes and the virtual clothes by himself. Therefore, if the user wants to view the try-on wearing effect of a real clothes, the user needs to carefully check the virtual clothes list, compare the plurality of virtual clothes in the virtual clothes list with the real clothes one by one, and then select the virtual clothes corresponding to the real clothes. If there are too many virtual clothes in the virtual clothes list, the user needs to spend a considerable amount of time searching and selecting, which reduces the user experience.

[0123] Therefore, in order to improve the user experience of showing the wearing effect of the real clothes based on the virtual clothes, the present application provides a clothes try-on method and a clothes try-on device for implementing the clothes try-on method.

[0124] Specifically, FIG. 2 is a structural schematic diagram of a clothes try-on device according to an embodiment of the present application.

[0125] In an implementation example, as shown in FIG. 2, the clothes try-on device 104 includes an image acquisition module 110, a virtual clothes matching module 130, a virtual human body construction module 140, a try-on module 150, and a display module 160.

[0126] The image acquisition module 110 is configured to acquire an image of a real clothes that the user wants to try on and wear.

[0127] In the embodiment of the present application, the clothes that the user wants to try on and wear include but are not limited to clothes (e.g., tops, T-shirts, vests, shorts, pants, etc.), jewelry, hats, shoes, etc.

[0128] In the embodiment of the present application, the image of the real clothes includes but is not limited to a picture, a video, etc. of the real clothes.

[0129] The image acquisition module 110 outputs the image of the real clothes to the virtual clothes matching module 130. The virtual clothes matching module 130 is connected to a virtual asset library.

[0130] The virtual asset library is configured to save 3D assets. A 3D asset is a digital file used to represent a 3D object, which generally includes information such as a mesh, vertices, textures, materials, and physical parameters that make up the asset.

[0131] In the embodiments of the present application, the virtual asset library is used to store the 3D asset (virtual clothes model) corresponding to the real clothes.

[0132] Further, in an embodiment, the virtual asset library can be a local database stored in the computing device 100, or a cloud database stored in a cloud server.

[0133] The virtual clothes matching module 130 is used to search in the virtual asset library according to the image of the real clothes, and obtain the try-on clothes model according to the search result and output.

[0134] The virtual human body construction module 140 is used to generate a virtual human body model. The virtual human body model is a digital file used to represent a 3D human body. The virtual human body model is not worn with virtual clothes.

[0135] The try-on module 150 is used to perform virtual clothes try-on based on the virtual human body model output by the virtual human body construction module 140, according to the try-on clothes model output by the virtual clothes matching module 130, to obtain a virtual wearing model, which is a model of a virtual human body wearing virtual clothes.

[0136] Specifically, the try-on module 150 combines the virtual human body model and the try-on clothes model to obtain the virtual wearing model.

[0137] For example, the try-on module 150 realizes virtual clothes try-on based on 3D simulation. The try-on module 150 simulates the state of the 3D asset (try-on clothes model) corresponding to the real clothes moving with the 3D human body (virtual human body model) based on a physical engine or a physical simulation algorithm.

[0138] In an embodiment, the virtual wearing model output by the try-on module 150 contains the 3D positions of the grid vertices of each frame of the try-on clothes model and the virtual human body model.

[0139] The display module 160 is used to perform image rendering based on the virtual wearing model output by the try-on module 150, to generate a virtual character image wearing virtual clothes, and to display the virtual character image wearing virtual clothes to the user.

[0140] FIG. 3 is a flowchart of a clothes try-on method according to an embodiment of the present application.

[0141] In an embodiment, the computing device shown in FIG. 2 performs the following flow shown in FIG. 3 to assist the user in clothes try-on.

[0142] S200, the image acquisition module 110 acquires at least one image of real clothes.

[0143] Optionally, in an embodiment, the at least one image of the real clothes acquired by the image acquisition module 110 comprises one or more pictures of the real clothes, and / or one or more videos of the real clothes.

[0144] For example, in an embodiment, the at least one image of the real clothes comprises a plurality of pictures of the real clothes, each picture being for an angle of the real clothes. For example, the plurality of pictures of the real clothes comprises a front picture, a back picture, a left side picture and a right side picture of the real clothes.

[0145] For another example, in an embodiment, the at least one image of the real clothes comprises a video of the real clothes, the video being a video generated by surrounding shooting of the real clothes, or the video being a video generated by shooting of the real clothes in a process of rotating the real clothes.

[0146] Optionally, in an embodiment, the at least one image of the real clothes acquired by the image acquisition module 110 is a pre-stored image.

[0147] For example, the image acquisition module 110 acquires a picture selected by the user (e.g., a picture of clothes selected from a local gallery or a network) as the image of the real clothes according to a selection operation of the user.

[0148] Optionally, in another embodiment, the image acquisition module 110 live shoots the real clothes provided by the current user to acquire the image of the real clothes.

[0149] Specifically, in an embodiment, the image acquisition module 110 is connected to a camera, and the image acquisition module 110 uses the camera to acquire an image of the real clothes expected to be tried on by the user to acquire the image of the real clothes.

[0150] Further, in order to acquire a complete image of the real clothes, in an embodiment, a prompt is outputted to prompt the user to adopt an optimal image acquisition manner to acquire the image in a process of acquiring the image of the real clothes by the image acquisition module 110.

[0151] For example, the user is prompted to take pictures of the front, back, left side and right side of the real clothes respectively; for another example, the user is prompted to change the shooting angle of the camera or rotate the real clothes in a process of video shooting.

[0152] Further, in an embodiment, after acquiring the image of the real clothes, the image acquisition module 110 analyzes the acquired image of the real clothes to confirm whether the acquired image of the real clothes is sufficient to support a subsequent retrieval operation, and further acquires more images if the acquired image is insufficient.

[0153] For example, the image collection module 110 analyzes the pictures of the real clothes, confirms that the pictures contain front pictures and back pictures of the real clothes, but lack left and right pictures, and prompts the user to collect images of the left and right sides of the real clothes.

[0154] For another example, the image collection module 110 analyzes the video of the real clothes, confirms that the video screen has severe shaking, resulting in blurred images, and prompts the user to re-shoot a clearer and more stable video.

[0155] According to the method of the embodiment of the application, the images of the real clothes are obtained by collecting pictures / videos on site and / or calling existing pictures / videos, which can improve the recognition accuracy of the real clothes and improve the recognition success rate of the real clothes.

[0156] In S201, the virtual clothes matching module 130 performs matching retrieval in the plurality of virtual clothes models according to the at least one image of the real clothes obtained by the image collection module 110, obtains a retrieval result, and obtains a try-on clothes model according to the retrieval result.

[0157] Specifically, in an embodiment, the plurality of virtual clothes models in S201 are part or all of the virtual clothes models stored in the virtual asset library. In subsequent embodiments, the plurality of virtual clothes models stored in the virtual asset library are referred to as the virtual asset library.

[0158] Specifically, in an embodiment, the virtual clothes matching module 130 uses a neural network model to perform matching retrieval in the plurality of virtual clothes models. For example, the neural network model calculates the matching degree of each of the plurality of virtual clothes models and the image of the real clothes.

[0159] Specifically, in an embodiment, the virtual clothes matching module 130 inputs the at least one image of the real clothes obtained by the image collection module 110 into the neural network model to obtain one or more first virtual clothes models. The try-on clothes model is obtained according to the one or more first virtual clothes models.

[0160] According to the method of the embodiment of the application, the neural network model is used to implement the matching retrieval of the virtual clothes model, which reduces the implementation difficulty of the matching retrieval and improves the reliability of the matching retrieval.

[0161] Further, in an embodiment, in S201, the virtual clothes matching module 130 first filters the plurality of virtual clothes models according to the at least one image of the real clothes obtained by the image collection module 110, performs matching retrieval in the filtering result, obtains a retrieval result, and obtains a try-on clothes model according to the retrieval result.

[0162] For example, in an embodiment, the virtual clothes matching module 130 identifies the attribute of the real clothes according to the image of the real clothes, the attribute of the real clothes including but not limited to the color, the style, etc. of the clothes. For example, the attribute of a real clothes is "gray short down jacket". The virtual clothes matching module 130 filters the virtual clothes models according to the attribute of the real clothes, and selects the virtual clothes models consistent with the attribute of the real clothes. The virtual clothes matching module 130 performs matching search among the selected virtual clothes models according to the image of the real clothes.

[0163] Optionally, in an embodiment, in S201, the virtual clothes matching module 130 searches the virtual clothes model with the highest matching degree with the image of the real clothes from the plurality of virtual clothes models, and outputs the virtual clothes model as the try-on clothes model.

[0164] Optionally, in an embodiment, in S201, the virtual clothes matching module 130 searches one or more first virtual clothes models with the matching degree exceeding a first preset value (for example, 90%) from the plurality of virtual clothes models. The virtual clothes matching module 130 obtains the try-on clothes model according to the one or more first virtual clothes models.

[0165] According to the method of the embodiments of the present application, the virtual clothes corresponding to the real clothes is searched based on the preset matching degree threshold, which can avoid the user to manually search the virtual clothes from the plurality of virtual clothes, and simplifies the user operation.

[0166] Specifically, in an embodiment, when the first virtual clothes model with the matching degree exceeding the first preset value is one, the first virtual clothes model is taken as the try-on clothes model.

[0167] Alternatively, in another embodiment, when the first virtual clothes model with the matching degree exceeding the first preset value is one, the first virtual clothes model is output to the display module 160, the display module 160 performs image rendering based on the first virtual clothes model, and generates the virtual clothes image to display to the user (the virtual clothes image can be a static image or a dynamic image, and the virtual clothes image can be a 2D image or a 3D image with adjustable viewing angle). The confirmation instruction or the cancel instruction of the user is received, the confirmation instruction is used to indicate that the user determines to try on the first virtual clothes model, and the cancel instruction is used to indicate that the user gives up to try on the first virtual clothes model. According to the confirmation instruction of the user, the first virtual clothes model is taken as the try-on clothes model. Alternatively, according to the cancel instruction of the user, the current try-on process is ended.

[0168] Specifically, in an embodiment, when there are multiple first virtual clothing models whose matching degrees exceed the first preset value, the multiple first virtual clothing models are output to the display module 160, the display module 160 performs image rendering based on the multiple first virtual clothing models, and generates multiple virtual clothing images to be displayed to the user (the virtual clothing image can be a static image or a dynamic image, and the virtual clothing image can be a 2D image or a 3D image with adjustable viewing angles). A selection instruction or a cancellation instruction of the user is received. The selection instruction is used to indicate a selected virtual clothing image of the user in the multiple virtual clothing images, and the cancellation instruction is used to indicate that the user gives up trying on all the first virtual clothing models. According to the selection instruction of the user, the first virtual clothing model corresponding to the virtual clothing image selected by the user is taken as the try-on clothing model. Alternatively, according to the cancellation instruction of the user, the current try-on process is ended.

[0169] According to the method of the embodiment of the present application, the user performs final confirmation on the premise of searching for the virtual clothing corresponding to the real clothing through the matching degree, which improves the accuracy of the real clothing recognition result and improves the user experience of the virtual clothing try-on and try-wearing.

[0170] Further, in an embodiment, when there is no first virtual clothing model whose matching degree exceeds the first preset value in the multiple virtual clothing models, or after the display module 160 displays the virtual clothing image of the first virtual clothing model to the user, the user indicates that there is no virtual clothing image expected to be tried on in the displayed virtual clothing image, the virtual clothing matching module 130 outputs prompt information to the user through the display module 160 or in a voice manner, and informs the user that the try-on and try-wearing display cannot be realized for the current real clothing.

[0171] For example, FIG. 4 is a partial flowchart of a clothing try-on method according to an embodiment of the present application.

[0172] In an embodiment, the virtual clothing matching module 130 performs the following process shown in FIG. 4 to obtain the try-on clothing model.

[0173] S210, an image of a real clothing is obtained.

[0174] S211, a virtual clothing model whose matching degree with the image of the real clothing exceeds a first preset value is searched for in a virtual asset library.

[0175] If one or more first virtual clothing models whose matching degrees with the image of the real clothing exceed the first preset value are searched for in the virtual asset library, S212 is performed.

[0176] S212, the one or more first virtual clothing models are output to the display module 160 to display virtual clothing images of the one or more first virtual clothing models to the user.

[0177] Specifically, the display module 160 performs image rendering on the one or more first virtual clothes models to generate one or more virtual clothes images respectively corresponding to the one or more first virtual clothes models. The display module 160 provides a virtual clothes selection page for displaying the one or more virtual clothes images.

[0178] S213, receiving a selection instruction of the user, the selection instruction being used to indicate a virtual clothes image selected by the user, and according to the selection instruction of the user, taking the first virtual clothes model corresponding to the virtual clothes image selected by the user as the clothes model for trying on.

[0179] If no virtual clothes model with a matching degree exceeding the first preset value is searched in the virtual asset library, S214 is performed.

[0180] S214, instructing the display module 160 to display notification information, the notification information being used to notify the user that the current real clothes cannot be tried on.

[0181] Further, in another embodiment, when no virtual clothes model with a matching degree exceeding the first preset value exists in the virtual asset library, or when the user indicates that no virtual clothes image desired to be tried on exists in the virtual clothes images displayed by the display module 160 to the user, the virtual clothes matching module 130 searches in the virtual asset library according to the image of the real clothes, searches virtual clothes models respectively matching the clothes style and the clothes color and pattern of the real clothes, synthesizes the clothes style of the virtual clothes model matching the clothes style and the clothes color and pattern of the virtual clothes model matching the clothes color and pattern to generate a new virtual clothes model, and obtains the clothes model for trying on according to the new virtual clothes model.

[0182] For example, FIG. 5 is a partial flowchart of a clothes trying-on method according to an embodiment of the present application.

[0183] In an embodiment, the virtual clothes matching module 130 performs the following process shown in FIG. 5 to obtain the clothes model for trying on.

[0184] S220, obtaining the image of the real clothes.

[0185] S221, searching in the virtual asset library for a virtual clothes model with a matching degree exceeding a first preset value with the image of the real clothes.

[0186] If one or more first virtual clothes models with a matching degree exceeding the first preset value with the image of the real clothes are searched in the virtual asset library, S222 is performed.

[0187] S222, outputting the one or more first virtual clothes models to the display module 160 to display virtual clothes images of the one or more first virtual clothes models to the user.

[0188] S223, receiving a selection instruction of the user, the selection instruction being used to indicate a virtual clothes image selected by the user, and according to the selection instruction of the user, taking the first virtual clothes model corresponding to the virtual clothes image selected by the user as the try-on clothes model.

[0189] If no virtual clothes model with a matching degree exceeding the first preset value is searched in the virtual asset library, S224 is performed.

[0190] S224, searching for a virtual clothes model with a clothes style matching degree exceeding a second preset value and a virtual clothes model with a clothes pattern matching degree exceeding a third preset value in the virtual asset library.

[0191] Specifically, the second preset value and the third preset value can be the same as (for example, both 90%) or different from (for example, the first preset value is 90%, the second preset value is 80%, and the third preset value is 85%) the first preset value.

[0192] If one or more second virtual clothes models with a clothes style matching degree exceeding the second preset value and one or more third virtual clothes models with a clothes pattern matching degree exceeding the third preset value are searched in the virtual asset library, S225 is performed.

[0193] S225, generating one or more fourth virtual clothes models according to the one or more second virtual clothes models and the one or more third virtual clothes models, wherein the clothes style of the fourth virtual clothes model matches the second virtual clothes model, and the clothes pattern of the fourth virtual clothes model matches the third virtual clothes model.

[0194] S226, obtaining the try-on clothes model according to the one or more fourth virtual clothes models.

[0195] The implementation of S226 can refer to the process of obtaining the try-on clothes model according to the one or more first virtual clothes models provided above.

[0196] For example, the one or more fourth virtual clothes models are output to the display module 160 to display virtual clothes images of the one or more fourth virtual clothes models to the user. A selection instruction of the user is received, the selection instruction being used to indicate a virtual clothes image selected by the user, and according to the selection instruction of the user, the fourth virtual clothes model corresponding to the virtual clothes image selected by the user is taken as the try-on clothes model.

[0197] For another example, the matching degrees of the plurality of fourth virtual clothes models and the image of the real clothes are calculated respectively, and one fourth virtual clothes model with the highest matching degree with the image of the real clothes is taken as the try-on clothes model.

[0198] If no virtual clothes model with a clothes style matching degree with the image of the real clothes exceeding the second preset value is retrieved in the virtual asset library, or no virtual clothes model with a clothes pattern matching degree with the image of the real clothes exceeding the third preset value is retrieved in the virtual asset library, S228 is performed.

[0199] S228, instructing the display module 160 to display notification information informing the user that try-on and try-wearing cannot be performed for the current real clothes.

[0200] According to the method of the embodiments of the present application, in the case that the virtual clothes corresponding to the real clothes cannot be obtained through matching, the virtual clothes corresponding to the real clothes are obtained by combining the clothes style and the clothes pattern of the existing virtual clothes, the accuracy of the real clothes recognition result is improved, the success rate of obtaining the virtual clothes corresponding to the real clothes is improved, and the user experience of virtual clothes try-on and try-wearing is improved.

[0201] Further, in another embodiment, when no virtual clothes model with a matching degree exceeding the first preset value exists in the virtual asset library, or when the user indicates that no virtual clothes image desired to be tried on exists in the virtual clothes image displayed by the display module 160 to the user after the virtual clothes image of the first virtual clothes model is displayed, the virtual clothes matching module 130 performs 3D virtual modeling according to the image of the real clothes, creates a virtual clothes model matching the image of the real clothes, and takes the newly created virtual clothes model as the try-on clothes model.

[0202] For example, FIG. 6 is a partial flowchart of a clothes try-on method according to an embodiment of the present application.

[0203] In an embodiment, the virtual clothes matching module 130 performs the following process shown in FIG. 6 to generate the try-on clothes model.

[0204] S230, obtaining the image of the real clothes.

[0205] S231, retrieving, in the virtual asset library, a virtual clothes model with a matching degree with the image of the real clothes exceeding the first preset value.

[0206] If one or more first virtual clothes models with a matching degree with the image of the real clothes exceeding the first preset value are retrieved in the virtual asset library, S232 is performed.

[0207] S232, output the one or more first virtual clothes models to the display module 160 to display virtual clothes images of the one or more first virtual clothes models to the user.

[0208] S233, receive a selection instruction of the user, the selection instruction being used to indicate a virtual clothes image selected by the user, and according to the selection instruction of the user, take the first virtual clothes model corresponding to the virtual clothes image selected by the user as the try-on clothes model.

[0209] If no virtual clothes model with a matching degree exceeding the first preset value is searched from the virtual asset library, S234 is performed.

[0210] S234, perform 3D modeling according to the image of the real clothes to generate one or more fifth virtual clothes models.

[0211] S235, obtain the try-on clothes model according to the one or more fifth virtual clothes models.

[0212] The implementation of S235 can refer to the process of obtaining the try-on clothes model according to the one or more first virtual clothes models provided previously.

[0213] For example, the one or more fifth virtual clothes models are output to the display module 160 to display virtual clothes images of the one or more fifth virtual clothes models to the user. A selection instruction of the user is received, the selection instruction being used to indicate a virtual clothes image selected by the user, and according to the selection instruction of the user, the fifth virtual clothes model corresponding to the virtual clothes image selected by the user is taken as the try-on clothes model.

[0214] According to the method of the embodiments of the present application, in the case that the virtual clothes corresponding to the real clothes cannot be obtained through matching degree searching, the virtual clothes model corresponding to the real clothes is obtained through 3D modeling according to the image of the real clothes, the accuracy of the identification result of the real clothes is improved, the success rate of obtaining the virtual clothes corresponding to the real clothes is improved, and the user experience of virtual clothes try-on and try-wearing is improved.

[0215] Further, in an embodiment, in the case that the virtual clothes corresponding to the real clothes cannot be obtained through matching degree searching, the virtual clothes corresponding to the real clothes are first generated by combining the clothes styles and patterns of the existing virtual clothes (refer to the embodiment shown in FIG. 5). When the virtual clothes pattern or clothes style corresponding to the real clothes cannot be searched, the virtual clothes model corresponding to the real clothes is generated through 3D modeling according to the image of the real clothes.

[0216] Further, in an embodiment, the image of the real garment acquired by the image acquisition module 110 in S200 can contain identification information of the real garment, which is used to describe the garment style / color of the real garment, and / or the brand / manufacturer of the real garment, and / or the order information of the real garment, and / or the product number of the real garment, etc.

[0217] For example, the image of the real garment can contain a garment style number picture of the real garment, and / or a two-dimensional code picture corresponding to the garment style of the real garment, and / or a picture containing text information of the brand / manufacturer of the real garment, and / or a two-dimensional code picture of the brand / manufacturer of the real garment, and / or an order picture of the real garment, and / or a product information picture of the real garment, etc.

[0218] In S201, the virtual garment matching module 130 performs retrieval in the virtual asset library according to the identification information contained in the image of the real garment.

[0219] In S202, the virtual human body construction module 140 acquires a virtual human body model.

[0220] Specifically, in an embodiment, the virtual human body model acquired by the virtual human body construction module 140 in S202 is not worn with a virtual garment.

[0221] Optionally, in an embodiment, the virtual human body model acquired by the virtual human body construction module 140 in S202 is a pre-defined virtual human body template model. The virtual human body construction module 140 directly acquires a default virtual human body template model as the virtual human body model, or the virtual human body construction module 140 calls a corresponding virtual human body template model from a plurality of virtual human body template models as the virtual human body model according to the personal body information (e.g., gender) input by the user.

[0222] Optionally, in another embodiment, the virtual human body model acquired by the virtual human body construction module 140 in S202 is a virtual human body model pre-generated for the current user.

[0223] For example, the virtual human body construction module 140 calls the virtual human body model corresponding to the user in the database according to the user identity.

[0224] Specifically, in an embodiment, the database for saving the virtual human body model can be a local database or a cloud database.

[0225] Specifically, in an embodiment, the virtual human body model saved in the database can be a virtual human body model generated by the virtual human body construction module 140, or a virtual human body model generated by other computing devices.

[0226] In an embodiment, the virtual human body construction module 140 generates a virtual human body model for the user based on the pre-defined virtual human body template model and the user inputted personal body information, and saves the generated virtual human body model to the database.

[0227] Specifically, in an embodiment, the user inputted personal body information can be specific user body data, for example, the personal body information includes but is not limited to gender, height, weight, bust, waist, hip, leg circumference, foot size, etc.

[0228] In another embodiment, the user inputted personal body information can be a broad description of the user's body features, for example, the personal body information includes but is not limited to fat, thin, etc.

[0229] Optionally, in another embodiment, in S202, the virtual human body model output by the virtual human body construction module 140 in S202 is a virtual human body model generated in real time by the virtual human body construction module 140 based on the pre-defined virtual human body template and the user inputted personal body information.

[0230] Further, in an embodiment, the virtual human body construction module 140 outputs the virtual human body model to the display module 160. The display module 160 performs image rendering based on the virtual human body model to generate a virtual human body image corresponding to the virtual human body model and display it to the user.

[0231] In an embodiment, the virtual human body image corresponding to the virtual human body model is a virtual three-dimensional human body image without virtual clothes.

[0232] Optionally, in an embodiment, a body information input interface is provided to the user at the same time as the virtual human body image is displayed, so that the user can adjust the virtual human body model with reference to the displayed virtual human body image.

[0233] Further, in an embodiment, the virtual human body construction module 140 acquires a picture or video of the user's body, performs three-dimensional modeling based on the picture or video of the user's body, and generates a virtual human body model of the user.

[0234] S203, the try-on module 150 combines the virtual human body model output by the virtual human body construction module 140 and the try-on clothes model output by the virtual clothes matching module 130 to obtain a virtual wearing model, so as to realize virtual human body trying on virtual clothes. The virtual wearing model is a model of a virtual human body wearing virtual clothes.

[0235] Optionally, in an embodiment, in S203, the virtual wearing model obtained by the try-on module 150 contains only the virtual clothes model output by the virtual clothes matching module 130.

[0236] Optionally, in an embodiment, in S203, the virtual wearing model obtained by the try-on module 150 has virtual clothes that not only include the try-on clothes model output by the virtual clothes matching module 130, but also include virtual clothes models matched with the try-on clothes model.

[0237] Specifically, in an embodiment, the try-on module 150 obtains, from the virtual asset library, a virtual clothes model matched with the try-on clothes model according to the try-on clothes model. The try-on module 150 combines the virtual human model, the try-on clothes model, and the virtual clothes model matched with the try-on clothes model to obtain the virtual wearing model.

[0238] According to the method of the embodiment of the present application, the virtual clothes model matched with the try-on clothes model is obtained, and the try-on clothes model and the virtual clothes model matched with the try-on clothes model are both worn on the virtual human model, and the virtual character image wearing the complete set of virtual clothes is displayed to the user, which optimizes the virtual clothes try-on effect of the virtual character image, improves the visual effect of the virtual character image, and improves the user experience of the virtual clothes try-on and wearing.

[0239] For example, FIG. 7 is a partial flowchart of a clothes try-on method according to an embodiment of the present application.

[0240] In an embodiment, the try-on module 150 performs the following process shown in FIG. 7 to obtain the virtual wearing model.

[0241] S240, obtaining the virtual human model output by the virtual human structure module 140 and the try-on clothes model output by the virtual clothes matching module 130.

[0242] S241, obtaining, from the virtual asset library, a virtual clothes model matched with the try-on clothes model.

[0243] S242, combining the virtual human model, the try-on clothes model, and the virtual clothes model matched with the try-on clothes model to obtain the virtual wearing model.

[0244] Optionally, in an embodiment, in S710, the try-on module 150 requests the user to input clothes information matched, and searches for the virtual clothes model with the highest matching degree with the clothes information input by the user from the plurality of virtual clothes models as the virtual clothes model matched with the try-on clothes model according to the clothes information input by the user.

[0245] For example, the user inputs “white shirt and black pants” as the clothes information matched with the try-on clothes. The try-on module 150 searches for the virtual clothes model with the highest matching degree with “white shirt” and “black pants” respectively from the virtual asset library as the virtual clothes model matched with the try-on clothes model.

[0246] Optionally, in another embodiment, in S710, the try-on module 150 obtains, according to the try-on clothes model, a virtual clothes model matched with the try-on clothes model.

[0247] Specifically, in an embodiment, in S710, the try-on module 150 acquires clothes features corresponding to the try-on clothes model, which include clothes type and / or clothes color. The try-on module 150 determines clothes features matched with the try-on clothes model according to the clothes features corresponding to the try-on clothes model; and acquires a virtual clothes model matched with the try-on clothes model based on the clothes features matched with the try-on clothes model.

[0248] For example, in an embodiment, the try-on module 150 acquires clothes type (e.g., T-shirt, short-sleeve outerwear, long-sleeve outerwear, round-neck pullover long-sleeve sportswear, etc.) and clothes color corresponding to the try-on clothes model according to the try-on clothes model output by the virtual clothes matching module 130.

[0249] The try-on module 150 determines clothes type that needs to be matched according to the clothes type corresponding to the try-on clothes model. And the try-on module 150 determines color corresponding to the clothes type that needs to be matched according to the clothes color corresponding to the try-on clothes model based on the clothes type that needs to be matched.

[0250] The try-on module 150 searches for virtual clothes models in the virtual asset library according to the clothes type that needs to be matched and the color, and takes the virtual clothes model with the highest matching degree with the clothes type that needs to be matched and the color as the virtual clothes model matched with the try-on clothes model.

[0251] For example, the clothes corresponding to the try-on clothes model is a black suit coat. The try-on module 150 determines that the clothes type corresponding to the try-on clothes model is suit coat according to the try-on clothes model. The try-on module 150 determines that the clothes type that needs to be matched is shirt, necktie, trousers and shoes according to the suit coat. The try-on module 150 determines that the color of the shirt that needs to be matched is white, the color of the trousers that needs to be matched is black, the color of the shoes that needs to be matched is black, and the color of the necktie that needs to be matched is blue according to the color of the suit coat being black based on the suit coat.

[0252] Optionally, in another embodiment, in S710, the try-on module 150 recommends clothes that can be selected for matching to the user according to the try-on clothes model output by the virtual clothes matching module 130, and acquires a virtual clothes model matched with the try-on clothes model according to the user selection operation.

[0253] For example, in an embodiment, the try-on module 150 determines a type of clothes (e.g., T-shirt, short-sleeve outerwear, long-sleeve outerwear, round-neck pullover long-sleeve sportswear, etc.) corresponding to the try-on clothes model according to the try-on clothes model output by the virtual clothes matching module 130. The try-on module 150 determines a type of clothes that needs to be matched according to the type of clothes corresponding to the try-on clothes model. The try-on module 150 determines a color corresponding to the type of clothes that needs to be matched according to the color of the clothes corresponding to the try-on clothes model based on the type of clothes that needs to be matched. The try-on module 150 searches the virtual clothes models saved in the virtual asset library according to the type of clothes that needs to be matched and the color, and outputs a plurality of virtual clothes models that are most matched with the type of clothes that needs to be matched and the color to the display module 160 for the user to select one of them as a virtual clothes model matched with the try-on clothes model.

[0254] In S204, the display module 160 performs image rendering based on the virtual wearing model output by the try-on module 150 to generate a virtual person image wearing virtual clothes and display it to the user.

[0255] In S204, the virtual person image is a virtual three-dimensional person image or a virtual two-dimensional person image containing virtual clothes.

[0256] According to the method and clothes try-on device of the embodiments of the present application, the try-on and wearing of the virtual clothes corresponding to the real clothes can be realized by recognizing the real clothes, the process of the virtual clothes try-on and wearing is simplified, and the user experience of the virtual clothes try-on and wearing is improved.

[0257] Further, in an embodiment, the method further comprises configuring a body action of the virtual person image.

[0258] Specifically, in an embodiment, in S204, the action configuration parameter is obtained. The virtual wearing model is adjusted according to the action configuration parameter, so that the body action corresponding to the virtual wearing model matches the action configuration parameter.

[0259] For example, in an embodiment, the display module 160 displays an action setting interface containing action buttons (e.g., sitting posture 1, sitting posture 2, standing posture 1, standing posture 2) (different action buttons correspond to different actions). The virtual human body construction module 140 adjusts the virtual human body model according to the action button clicked by the user, so that the body action corresponding to the virtual human body model matches the action button clicked by the user.

[0260] For example, in another embodiment, the display module 160 displays a 3D virtual human image corresponding to the virtual human model. The user can change the action corresponding to the 3D virtual human image by dragging the body part (e.g., left hand, left upper arm, left lower arm, chest, waist, etc.) of the 3D virtual human image. The virtual human configuration module 140 adjusts the virtual human model according to the change of the 3D virtual human image, so that the body action corresponding to the virtual human model matches the action of the 3D virtual human image.

[0261] Further, in an embodiment, the method further comprises configuring the display scene of the virtual character image.

[0262] Specifically, in an embodiment, the display scene of the virtual character image includes display parameters (e.g., light intensity, light source type, light source color, light angle, etc.) of the virtual character image, and / or background image (e.g., 2D background and / or 3D background) of the virtual character image, and / or display environment (e.g., weather) of the background image of the virtual character image.

[0263] For example, in an embodiment, the display module 160 displays a scene setting interface (different background buttons correspond to different background images) including background buttons (e.g., home 1, home 2, office, outdoor). The display module 160 calls the corresponding background image according to the background button clicked by the user, and displays the background image and the virtual character image superimposed.

[0264] Further, in an embodiment, before S202, configuration information (action configuration parameters) of the body action is obtained. In S202, the virtual human configuration module 140 adjusts the virtual human model according to the action configuration parameters, and outputs the virtual human model whose body action matches the action configuration parameters.

[0265] Before S203, configuration information (display scene configuration parameters) of the display scene is obtained. In S203, the virtual try-on module 150 simulates based on the virtual human model output by the virtual human configuration module 140, the try-on clothes model output by the virtual clothes matching module 130, and the display scene configuration parameters, realizes virtual clothes try-on and superposition of the real scene, and generates virtual wearing model + real scene data. Therefore, in S204, the display module 160 displays images based on the virtual wearing model + real scene data, and displays the display scene and the virtual character image in the display scene for the user.

[0266] Further, in another embodiment, before S202, configuration information (action configuration parameters) of the body action is obtained. In S202, the virtual human configuration module 140 adjusts the virtual human model according to the action configuration parameters, and outputs the virtual human model whose body action matches the action configuration parameters.

[0267] In S203, the try-on module 150 performs a first simulation process based on the virtual human model output by the virtual human construction module 140 and the try-on clothes model output by the virtual clothes matching module 130, realizes virtual clothes try-on, and generates a virtual wearing model containing virtual clothes.

[0268] In S204, configuration information (display scene configuration parameters) of a display scene is acquired, and the display module 160 performs a second simulation process based on the virtual wearing model and the display scene configuration parameters, realizes superposition of the virtual wearing model and real scene data, and displays the display scene and the virtual character image in the display scene for the user.

[0269] Further, in another embodiment, in S202, the virtual human construction module 140 outputs a virtual human model without limiting body action (for example, the virtual human model contains description information of movable joint nodes).

[0270] In S203, the try-on module 150 performs a first simulation process based on the virtual human model output by the virtual human construction module 140 and the try-on clothes model output by the virtual clothes matching module 130, realizes virtual clothes try-on, and generates a virtual wearing model without limiting body action (for example, the virtual wearing model contains description information of movable joint nodes).

[0271] In S204, configuration information (action configuration parameters) of body action and / or configuration information (display scene configuration parameters) of a display scene is acquired.

[0272] The display module 160 performs a second simulation process according to the action configuration parameters and / or the display scene configuration parameters and the virtual wearing model without limiting body action, realizes body action change of the virtual wearing model and / or superposition of the virtual wearing model and real scene data, and displays the display scene and the virtual character image in the display scene for the user.

[0273] In this way, without changing the try-on clothes, only adjusting the body action and / or the display scene, it is not necessary to perform the first simulation process for the try-on clothes model again, and only the second simulation process needs to be performed again, thereby reducing simulation calculation amount.

[0274] FIG. 8 is a flowchart of a clothes try-on method according to an embodiment of the present application.

[0275] In an embodiment, the computing device shown in FIG. 2 performs the following process shown in FIG. 3 to realize assisting the user to try on clothes.

[0276] S250, the image acquisition module 110 acquires an image of real clothes and outputs the acquired image of real clothes.

[0277] S251, the virtual clothes matching module 130 searches in the virtual asset library according to the image of the real clothes output by the image acquisition module 110, searches the virtual clothes model matching the image of the real clothes, obtains the try-on clothes model and outputs.

[0278] S252, the virtual human structure module 140 obtains and outputs the virtual human model, wherein the virtual human model contains the description information of the movable joint node, and the body action corresponding to the virtual human model is the default body action.

[0279] S253, the try-on module 150 simulates according to the virtual human model output by the virtual human structure module 140 and the try-on clothes model output by the virtual clothes matching module 130, combines the virtual human model and the try-on clothes model, and generates the virtual wearing model wearing the virtual clothes, wherein the virtual wearing model contains the description information of the movable joint node.

[0280] S254, the display module 160 simulates according to the action configuration parameter and the virtual wearing model, and / or simulates according to the display scene configuration parameter, realizes the body action change of the virtual wearing model and / or the superposition of the virtual wearing model + display scene, and displays the display scene and the virtual character image in the display scene for the user.

[0281] S255, the action configuration parameter and / or the display scene configuration parameter are obtained.

[0282] S256, the try-on clothes model is changed.

[0283] The method provided in the application is applied to a computing device, and the application does not limit the type of the computing device for implementing the clothes try-on method proposed in the application. Those skilled in the art can select a corresponding computing device to implement the clothes try-on method provided in the application according to the application scene requirement.

[0284] For example, in an embodiment, the clothes try-on device can be implemented through a terminal device containing a display device and an image acquisition device. The terminal device can be any terminal device that can interact with a user, such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, an augmented reality (AR) device, a VR device, etc.

[0285] Further, the application does not specifically limit the form of the interactive interface for implementing the clothes try-on method proposed in the application. Those skilled in the art can design the interactive interface for implementing the clothes try-on method proposed in the application according to the application scene requirement and the type of the computing device for implementing the clothes try-on method provided in the application.

[0286] For example, in an embodiment, the clothes try-on method proposed in the application is implemented by using a mobile phone.

[0287] FIG. 9 is a flow chart of a clothes fitting method according to an embodiment of the present application.

[0288] In an embodiment, the mobile phone performs the following flow shown in FIG. 9 to assist the user to fit clothes.

[0289] S300, the user starts the clothes fitting application on the mobile phone.

[0290] S301, the mobile phone acquires the virtual human body model of the current user.

[0291] Specifically, in an embodiment, the mobile phone first tries to call the virtual human body model of the current user saved locally on the mobile phone, and / or tries to call the virtual human body model of the current user saved on the cloud server according to the user identity information of the current user.

[0292] When the pre-saved virtual human body model cannot be called (for example, the virtual human body model of the current user is not saved locally and on the cloud server), the mobile phone screen displays a virtual human body setting interface for the user to input personal body information, and the mobile phone generates a virtual human body model according to the personal body information input by the user.

[0293] Further, in an embodiment, after the mobile phone generates a virtual human body model according to the personal body information input by the user, the mobile phone saves the generated virtual human body model to the mobile phone, or saves it to the cloud server.

[0294] S302, the mobile phone screen displays a virtual human body interface, the mobile phone performs image rendering according to the virtual human body model acquired in S301, generates a virtual human body image, and displays the virtual human body image in the virtual human body interface.

[0295] Further, in an embodiment, in S302, the virtual human body interface also provides a personal body information input interface for the user to input personal body information to adjust the virtual human body model, and as the user inputs personal body information, the virtual human body interface displays the latest virtual body image corresponding to the personal body information.

[0296] Further, in an embodiment, in S302, when the user inputs new personal body information, the mobile phone saves the virtual human body model corresponding to the latest personal body information to the mobile phone, or saves it to the cloud server to update the old virtual human body model.

[0297] For example, FIG. 10 is a schematic diagram of a mobile phone screen display interface according to an embodiment of the present application.

[0298] The mobile phone screen display interface is shown in FIG. 10 as 500, the user clicks the icon 501 of the clothes fitting application to start the clothes fitting application.

[0299] After S500, the phone interface is shown in 510 of FIG. 10, in which the user inputs the account name and password to verify the user identity. Alternatively, in another embodiment, the user has completed the identity verification on the phone, then skips the interface 510 and directly calls the identity verification result on the phone.

[0300] After the user identity verification is successful, the phone interface is shown in 520 of FIG. 10, in which the user inputs the personal body information (e.g. gender, height, weight, shoulder width, bust, waist, hip, leg circumference, foot size) for the phone to generate the virtual human body model. Alternatively, in another embodiment, the phone can call the pre-stored virtual human body model of the user according to the user’s identity information, then skips the interface 520 and directly calls the pre-stored virtual human body model of the user.

[0301] The phone displays the virtual human body interface as shown in 530 of FIG. 10, and the phone displays the virtual human body image (531) corresponding to the virtual human body model in the virtual human body interface according to the virtual human body model of the user. The virtual human body interface also provides a personal body information input interface (532) for the user to input the personal body information to adjust the virtual human body model.

[0302] The virtual human body interface provides a “try on” button 533 and a “quit” button 534. The user clicks the “try on” button 533 to enter the clothing try-on process. The user clicks the “quit” button 534 to exit the clothing try-on application.

[0303] S310, the phone enters the clothing try-on process based on the user operation, and the screen displays an image collection interface.

[0304] S320, the user performs image collection operation based on the image collection interface, uses the phone camera to take a photo or video of the real clothing, and obtains the image of the real clothing.

[0305] For example, FIG. 11 is a schematic diagram of the phone screen display interface according to an embodiment of the present application.

[0306] In an embodiment, the user clicks the “try on” button 533 in the virtual human body interface as shown in 530 of FIG. 10, and the phone starts the camera and displays the image collection interface as shown in 610 of FIG. 11. In the image collection interface, the viewfinder frame 611 displays the image taken by the camera. The image collection interface provides a “video” button 612, a “take a photo” button 613, an “import” button 614, a back button 615, and a “quit” button 616.

[0307] The user clicks the back button 615, and returns to the image collection interface shown in 530.

[0308] The user clicks the "exit" button 616 to exit the clothes fitting application.

[0309] After the user clicks the "video" button 612, the phone enters the video recording mode as shown in 620 of FIG. 11. In the video recording mode, the phone provides a record button 621, a stop recording button 622, a "fit" button 623, and an "exit" button 626. In the video recording mode, the phone prompts the user to "please rotate the clothes being photographed during the video shooting process" by text or voice.

[0310] After the user clicks the record button 621, the phone starts recording the camera shooting picture 627 as a video. After the user clicks the stop recording button 622, the phone stops recording the video, and the recorded video is displayed in the video list 624 below. The user clicks the record button 621 again to start recording a new video.

[0311] Each video in the video list 624 corresponds to a delete button 625. The user clicks the delete button 625 to delete the video from the video list 624.

[0312] The user clicks the "fit" button 623 to take all the videos in the video list 624 as images of real clothes.

[0313] The user clicks the return button 626 to return to the image collection interface shown in 610.

[0314] After the user clicks the "take a picture" button 613, the phone enters the picture taking mode as shown in 630 of FIG. 11, and the picture taking mode provides a picture taking button 631, a "fit" button 632, and a return button 633.

[0315] In the picture taking mode, the phone prompts the user to "please take pictures of the front, back, left, and right of the clothes" by text or voice.

[0316] After the user clicks the picture taking button 631, the phone takes the camera shooting picture 637 as a picture, and the taken picture is displayed in the picture list 634 below.

[0317] Each picture in the picture list 634 corresponds to a delete button 635. The user clicks the delete button 635 to delete the picture from the picture list 634.

[0318] The user clicks the "fit" button 632 to take all the pictures in the picture list 634 as images of real clothes.

[0319] The user clicks the return button 633 to return to the image collection interface shown in 610.

[0320] After the user clicks the "Import" button 614, the user enters the resource manager 647 shown in 640 of FIG. 11, which provides an "Import" button 641, a "Try on" button 642, and an "Exit" button 643.

[0321] The user expands or collapses a folder in the resource manager by clicking the folder, and selects or deselects a file by clicking the file. After the user selects the picture file and / or the video file, the user clicks the "Import" button 641, and the selected picture or video is displayed in the file list 645 below.

[0322] Each picture and video in the file list 645 corresponds to a delete button 646. The user clicks the delete button 646 to delete the picture or video from the file list 645.

[0323] The user clicks the "Try on" button 642 to use all the pictures and videos in the file list 645 as images of real clothes.

[0324] The user clicks the back button 643 to return to the image collection interface shown in 610.

[0325] S330, the phone searches in the virtual asset library of the cloud server based on the image of the real clothes, and retrieves one or more virtual clothes models matching the image of the real clothes.

[0326] S340, the phone displays a virtual clothes selection page, which is used to display one or more virtual clothes images corresponding to each of the one or more virtual clothes models matching the real clothes.

[0327] S341, the phone receives a selection instruction of the user, which indicates the virtual clothes image selected by the user, and according to the selection instruction, takes the virtual clothes model corresponding to the virtual clothes image selected by the user as a try-on clothes model.

[0328] S350, the phone displays a matching clothes selection interface, and based on the instruction of the user for the matching clothes selection interface, obtains a virtual clothes model matching the try-on clothes model.

[0329] S360, the phone combines the virtual human model, the try-on clothes model, and the virtual clothes model matching the try-on clothes model, to obtain a virtual wearing model wearing virtual clothes.

[0330] S370, the phone performs image rendering based on the virtual wearing model, generates a virtual character image wearing virtual clothes, and displays the virtual character image.

[0331] For example, FIG. 12 is a schematic diagram of a phone screen display interface according to an embodiment of the present application.

[0332] When the user clicks the "try on" button 623, or the "try on" button 632, or the "try on" button 642 in the interface shown in FIG. 11, the phone displays a virtual clothes selection page as shown in 700 of FIG. 12.

[0333] In 700, one or more virtual clothes images corresponding to one or more virtual clothes models matching the real clothes are displayed for the user to select and confirm. When there are too many alternative virtual clothes images to be displayed at one time, the user can swipe his finger on the interface of 700 to display different virtual clothes images.

[0334] A "confirm" button 701, a "re-identify" button 702, and a "quit" button 703 are provided in 700.

[0335] When the user clicks the "re-identify" button 702, the phone returns to the image capturing interface shown in 610.

[0336] The user clicks the "quit" button 703 to quit the clothes try-on application.

[0337] When the user selects a virtual clothes, the user clicks the "confirm" button 701 to confirm that the selected virtual clothes corresponds to the real clothes to be tried on, and the phone displays a virtual clothes display interface as shown in 710 of FIG. 12.

[0338] In 710, clothes types other than the type of the real clothes to be tried on are displayed, and the user is requested to select the type of virtual clothes to be matched.

[0339] For example, in an embodiment, the clothes types include hats, glasses, vests, T-shirts, shirts, coats, shorts, pants, shoes, etc. The real clothes to be tried on is a coat, and the clothes types displayed in 710 are hats, glasses, vests, T-shirts, shirts, shorts, pants, shoes, etc. The user confirms whether the clothes of the type is needed by checking the check box corresponding to the clothes type.

[0340] In 710, the user clicks a clothes type to enter a virtual clothes selection interface for the clothes type. For example, the user clicks the shirt type, and the phone displays a virtual clothes display interface as shown in 720 of FIG. 12. In 720, the user can select different virtual shirts (e.g., different colors and / or patterns).

[0341] A "confirm" button 721, a "back" button 722, and an "identify" button 723 are provided in 720.

[0342] After the user clicks the "OK" button 721, the user-selected virtual shirt is returned as a virtual clothing item for matching to the virtual clothing display interface 710.

[0343] After the user clicks the "back" button 722, the virtual clothing display interface 710 is directly returned.

[0344] After the user clicks the "identify" button 721, the image collection interface 610 is entered, and the virtual shirt for matching is confirmed through the identification of the real shirt.

[0345] The "OK" button 711, the "back" button 712, and the "exit" button 713 are provided in 710.

[0346] After the user clicks the "back" button 712, the virtual clothing display interface 700 is returned.

[0347] After the user clicks the "exit" button 713, the clothing fitting application is exited.

[0348] After the user clicks the "OK" button 711, all currently checked virtual clothing items are selected as virtual clothing items for matching, and virtual clothing fitting is performed.

[0349] For example, the user checks the shirt, the trousers, and the shoes, and clicks the shirt, the trousers, and the shoes, respectively, to complete the selection of the virtual shirt, the virtual trousers, and the virtual shoes. After the user clicks the "OK" button 711, fitting is performed for the virtual clothing item (the virtual coat) determined in 700 and the virtual clothing items for matching (the virtual shirt, the virtual trousers, and the virtual shoes) determined in 700. The mobile phone displays the virtual clothing wearing interface 730 shown in FIG. 12.

[0350] In the virtual human body image display window 731 of 730, a virtual human body image wearing the virtual clothing (the virtual coat, the virtual shirt, the virtual trousers, and the virtual shoes) is displayed.

[0351] Further, 730 provides action buttons (sitting posture 1, sitting posture 2, standing posture 1, standing posture 2, and standing posture 3). The user can click the action buttons to cause the virtual human body image display window 731 to present a virtual human body image corresponding to the action.

[0352] Further, 730 provides background buttons (home 1, home 2, office, outdoor 1, and outdoor 2). The user can click the background buttons to cause the virtual human body image display window 731 to present a corresponding background image.

[0353] Further, 730 provides an "identify again" button 732, a "match again" button 733, and an "exit" button 734.

[0354] When the user clicks the "re-identify" button 732, the image collection interface shown in 610 is returned.

[0355] When the user clicks the "re-identify" button 732, the image collection interface shown in 610 is returned.

[0356] When the user clicks the "exit" button 734, the clothing fitting application is exited.

[0357] For another example, in another embodiment, the clothing fitting method proposed in the present application is implemented using AR glasses.

[0358] FIG. 13 is a flowchart of a clothing fitting method according to an embodiment of the present application.

[0359] In an embodiment, the AR glasses implement the following process shown in FIG. 13 to assist the user in clothing fitting.

[0360] S800, the user starts the clothing fitting application on the AR glasses.

[0361] S801, the AR glasses display a clothing fitting interface, which contains an identification area.

[0362] In an embodiment of the present application, the identification area in the clothing fitting interface refers to one or more 2D or 3D areas visible in the AR glasses in the clothing fitting interface.

[0363] For example, FIG. 14 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application.

[0364] After the user starts the clothing fitting application on the AR glasses, the AR glasses displays the clothing fitting interface shown in FIG. 14 in the user's field of view.

[0365] The AR glasses display interface (clothing fitting interface) is a frame 900, and the identification area is the area marked by the frame 901.

[0366] S802, the AR glasses obtain the virtual human model of the current user.

[0367] Specifically, in an embodiment, after the clothing fitting application is started, the AR glasses call the virtual human model of the user based on the user's identity information.

[0368] When the AR glasses cannot call the virtual human model of the user, the AR glasses call a default virtual human model.

[0369] Further, in an embodiment, the clothes fitting interface provides a virtual human body loading button, when the user selects the virtual human body loading button, the AR glasses display a virtual human body loading interface for the user to input personal body information. The AR glasses generate a virtual human body model according to the personal body information input by the user.

[0370] As shown in FIG. 14, the clothes fitting interface (frame 900) provides a virtual human body loading button 903

[0371] S803, the AR glasses perform image rendering according to the virtual human body model, generate a virtual human body image, and display the virtual human body image in the clothes fitting interface.

[0372] In the embodiment of the present application, the virtual human body image corresponding to the virtual human body model is a virtual three-dimensional human body image without virtual clothes.

[0373] As shown in FIG. 14, the virtual human body image 902 is displayed in the middle of the AR glasses display interface, and the virtual human body image 902 is on the right side of the identification area (frame 901).

[0374] S810, the AR glasses perform image collection on the real clothes in the identification area, and obtain the image of the real clothes.

[0375] Specifically, in an embodiment, when the real clothes stay in the identification area for a short time, the AR glasses are triggered to perform image collection on the real clothes in the identification area. Optionally, the user can pick up the real clothes that the user wants to try on (for example, the user holds the clothes themselves or clothes hangers and the like), so that the real clothes stay in the identification area for a short time. Alternatively, the user can also move the visual angle so that the identification area in the line of sight coincides with the placement position of the real clothes, so that the real clothes stay in the identification area for a short time.

[0376] Specifically, in an embodiment, the real clothes staying in the identification area for a short time means that the real clothes are stationary in the identification area starting from the beginning to the continuous duration of maintaining stationary in the identification area reaching a preset time length (for example, 5 seconds).

[0377] Specifically, in an embodiment, when the real clothes stay in the identification area for a short time (the continuous duration of maintaining stationary reaches a preset time length), the AR glasses prompt to start identifying the clothes.

[0378] S820, the AR glasses perform retrieval in the virtual asset library of the cloud server based on the image of the real clothes, retrieve a virtual clothes model matching the image of the real clothes, and take the retrieved virtual clothes model matching the image of the real clothes as a fitting clothes model.

[0379] Specifically, in one embodiment, if the AR glasses retrieve a virtual clothing model that matches an image of real clothing, the user is prompted that the clothing has been identified and a try-on is in progress.

[0380] The S830 AR glasses combine a virtual human body model and a virtual clothing model to obtain a virtual wearable model wearing virtual clothing.

[0381] In S840, the AR glasses render images based on the virtual wearable model to generate a virtual character image wearing virtual clothing. This virtual character image is then displayed in the clothing try-on interface to replace the virtual human image displayed in S803.

[0382] In this embodiment of the application, the virtual character image corresponding to the virtual wearable model is a virtual three-dimensional human body image containing virtual clothing.

[0383] In this embodiment of the application, no specific restrictions are placed on the size, shape, or display method of the identification area.

[0384] In one embodiment, the identification area is the area defined by a visible frame in the clothing try-on interface. As shown in Figure 14, the rectangular frame 901 has visible frame boundaries.

[0385] In another embodiment, to simplify the user's visual interface, the boundaries of the recognition area are made invisible.

[0386] For example, Figure 15 is a schematic diagram of the display interface of AR glasses according to an embodiment of this application.

[0387] After a user launches the clothing try-on application on AR glasses, the AR glasses display the clothing try-on interface as shown in Figure 15 within the user's field of vision.

[0388] The AR glasses display interface (clothing try-on interface) is frame 1000, and the location of the recognition area is shown in frame 901 as shown in Figure 14.

[0389] As shown in Figure 15, there is no visible recognition area frame in frame 1000.

[0390] In another embodiment, the user's entire field of vision is used as the recognition area.

[0391] For example, as shown in Figure 15, frame 1000 is used as the recognition area.

[0392] In one embodiment, the identification area is a 2D area in the clothing try-on interface. As shown in Figure 14, the rectangular frame 901 is a 2D rectangular frame.

[0393] In another embodiment, the identification area is a 3D area in the clothing try-on interface.

[0394] For example, FIG. 16 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application.

[0395] After the user starts the clothes fitting application on the AR glasses, the AR glasses displays the clothes fitting interface as shown in FIG. 16 in the user's field of view.

[0396] The AR glasses display interface (clothes fitting interface) is a frame 1100, and the identification area is the area marked by the 3D rectangular frame 1101.

[0397] Further, in an embodiment, the identification area does not coincide with the display area of the virtual human body image (virtual character image). For example, as shown in FIG. 14, the identification area 901 does not coincide with the display area of the virtual human body image 902.

[0398] In another embodiment, the display area of the virtual human body image (virtual character image) is used as the identification area.

[0399] For example, when the real clothes temporarily stays in the display area of the virtual human body image (virtual character image), the AR glasses triggers image collection of the real clothes in the display area (identification area) of the virtual human body image.

[0400] FIG. 17 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application.

[0401] After the user starts the clothes fitting application on the AR glasses, the AR glasses displays the clothes fitting interface as shown in FIG. 17 in the user's field of view.

[0402] The AR glasses display interface (clothes fitting interface) is a frame 1200, and the identification area is the area marked by the 2D rectangular frame 1201.

[0403] The virtual human body image 1202 is displayed in the middle of the AR glasses display interface, and the display area of the virtual human body image 1202 is the identification area (frame 1201).

[0404] FIG. 18 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application.

[0405] After the user starts the clothes fitting application on the AR glasses, the AR glasses displays the clothes fitting interface as shown in FIG. 18 in the user's field of view.

[0406] The AR glasses display interface (clothes fitting interface) is a frame 1300, and the identification area is the area marked by the 3D rectangular frame 1301.

[0407] The virtual human body image 1302 is displayed in the middle of the AR glasses display interface, and the display area of the virtual human body image 1302 is the identification area (the frame 1301).

[0408] Further, in an embodiment, the virtual human body image display area is taken as the identification area, and the identification area is divided into areas of different human body parts based on the virtual human body image. When the real clothes temporarily stay at a certain human body part of the virtual human body image, the AR glasses trigger image collection of the real clothes in the human body part area (the identification area), and determine the wearing position of the real clothes according to the human body part where the real clothes temporarily stay.

[0409] FIG. 19 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application.

[0410] After the user starts the clothes fitting application on the AR glasses, the AR glasses displays the clothes fitting interface shown in FIG. 18 in the user's field of view.

[0411] The AR glasses display interface (the clothes fitting interface) is a frame 1400, and the identification area includes the areas marked by the 2D rectangular frames 1401, 1402, 1403, and 1404.

[0412] As shown in FIG. 19, the identification areas 1401, 1402, 1403, and 1404 are 2D planar rectangular areas corresponding to the head, the torso, the legs, and the feet of the virtual human body image 1405, respectively.

[0413] FIG. 20 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application.

[0414] After the user starts the clothes fitting application on the AR glasses, the AR glasses displays the clothes fitting interface shown in FIG. 20 in the user's field of view.

[0415] The AR glasses display interface (the clothes fitting interface) is a frame 1500, and the identification area includes the areas marked by the 3D rectangular frames 1501, 1502, 1503, and 1504.

[0416] As shown in FIG. 20, the identification areas 1501, 1502, 1503, and 1504 are 3D rectangular areas corresponding to the head, the torso, the legs, and the feet of the virtual human body image 1505, respectively.

[0417] FIG. 21 is a flowchart of a clothes fitting method according to an embodiment of the present application.

[0418] In an embodiment, the AR glasses perform the following flow shown in FIG. 21 to assist the user in clothes fitting.

[0419] S2100, the user starts the clothes fitting application on the AR glasses.

[0420] S2101, the AR glasses display a clothes fitting interface, the clothes fitting interface comprising a virtual clothes selection window.

[0421] The virtual clothes selection window is used to display a representative of a virtual clothes. The representative of a virtual clothes can be a clothes icon, a webpage, a link text, etc.

[0422] The representative of a virtual clothes in the virtual clothes list can be a clothes icon, a webpage, a link text, etc.

[0423] S2102, the AR glasses acquire a virtual human body model of the current user.

[0424] S2103, the AR glasses perform image rendering according to the virtual human body model, generate a virtual human body image, and display the virtual human body image in the clothes fitting interface.

[0425] S2110, the AR glasses receive a selection instruction of the user, the selection instruction being used to indicate a representative of a virtual clothes selected by the user in the virtual clothes selection window, and according to the selection instruction of the user, a virtual clothes model corresponding to the representative of the virtual clothes selected by the user is taken as a fitting clothes model.

[0426] For example, FIG. 22 is a schematic diagram of an AR glasses display interface according to an embodiment of the present application.

[0427] After the user starts the clothes fitting application on the AR glasses, the AR glasses displays the clothes fitting interface as shown in FIG. 20 in the user's visual range.

[0428] The AR glasses display interface (clothes fitting interface) is a frame 2200, and the identification area is an area marked by the frame 2201.

[0429] The virtual human body image 2202 is displayed in the middle of the AR glasses display interface, and the right side of the virtual human body image 2202 is the identification area (frame 2201).

[0430] The frame 2200 also displays a virtual clothes selection window 2203.

[0431] The user selects a representative of a virtual clothes in the virtual clothes selection window 2203, and the AR glasses confirms a virtual clothes model corresponding to the representative selected by the user as a fitting clothes model.

[0432] Optionally, in an embodiment, the user drags the representation of the virtual clothes from the virtual clothes list to the identification area 2201 for a short time to trigger the AR glasses to identify the virtual clothes corresponding to the dragged representation. The AR glasses take the identified virtual clothes as the virtual clothes selected by the user.

[0433] Optionally, in another embodiment, the user drags the representation of the virtual clothes from the virtual clothes list to the display area of the virtual human image 2202 for a short time to trigger the AR glasses to identify the virtual clothes corresponding to the dragged representation. The AR glasses take the identified virtual clothes as the virtual clothes selected by the user.

[0434] Alternatively, in another embodiment, no identification area is provided, and the user directly selects the virtual clothes from the virtual clothes list.

[0435] S2130, the AR glasses combine the virtual human model and the try-on clothes model to obtain a virtual try-on model wearing the virtual clothes.

[0436] S2140, the AR glasses perform image rendering according to the virtual try-on model to generate a virtual human image wearing the virtual clothes, and display the virtual human image in the clothes try-on interface to replace the virtual human image displayed in S2103.

[0437] FIG. 23 is a flowchart of a clothes try-on method according to an embodiment of the present application.

[0438] In an embodiment, the AR glasses perform the following process shown in FIG. 23 to assist the user in clothes try-on.

[0439] S2300, the user starts the clothes try-on application on the AR glasses.

[0440] S2301, the AR glasses display the clothes try-on interface, and the clothes try-on interface includes an identification area.

[0441] S2302, the AR glasses obtain the virtual human model of the current user.

[0442] S2303, the AR glasses perform image rendering based on the virtual human model to generate a virtual human image, and display the virtual human image in the clothes try-on interface (refer to the interface shown in FIG. 14).

[0443] S2310, the AR glasses perform image acquisition on the real clothes in the identification area to obtain the image of the real clothes.

[0444] S2311, the AR glasses perform search in the virtual asset library of the cloud server based on the image of the real clothes to search for a virtual clothes model matching the image of the real clothes.

[0445] S2320, the AR glasses display a virtual clothes selection window in the clothes fitting interface (refer to the interface shown in FIG. 22), and the virtual clothes selection window displays a virtual clothes image corresponding to a virtual clothes model matching the image of the real clothes.

[0446] S2321, the AR glasses receive a selection instruction of the user, the selection instruction is used to indicate the virtual clothes image selected by the user in the virtual clothes selection window, and the virtual clothes model corresponding to the virtual clothes image selected by the user is taken as a fitting clothes model according to the selection instruction of the user.

[0447] S2330, the AR glasses combine the virtual human model and the fitting clothes model to obtain a virtual wearing model wearing the virtual clothes.

[0448] S2340, the AR glasses perform image rendering based on the virtual wearing model to generate a virtual person image wearing the fitting clothes, and display the virtual person image in the clothes fitting interface to replace the virtual human image displayed in S2303.

[0449] In the description of the embodiments of the present application, in order to facilitate the description, the apparatus is described as various modules respectively, and the division of each module is only a logical function division, and in the implementation of the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0450] Specifically, the apparatus proposed in the embodiments of the present application can be integrated into a physical entity (for example, a GPU or other type of processor) in whole or in part, or can be physically separated. And these modules can be all in the form of software called by a processing element; or all in the form of hardware; or some modules are in the form of software called by a processing element, and some modules are in the form of hardware. For example, the detection module can be a separately set processing element, or can be implemented in a certain chip of the computing device. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or can be independently implemented. In the implementation process, each step of the above method or each module can be completed by the integrated logic circuit of hardware or the instruction of software in the processor element.

[0451] For example, the above modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), or one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, the modules can be integrated together to implement a System-On-a-Chip (SOC).

[0452] In an embodiment, the clothes fitting device provided in the present application can be implemented on a computing device, which contains all the modules of the clothes fitting device provided in the present application.

[0453] An embodiment of the present application further provides a computing device (for example, a mobile phone or AR glasses). The computing device is configured to execute the method processes or part of the method processes described in the embodiments of the present application.

[0454] FIG. 24 is a structural schematic diagram of a computing device according to an embodiment of the present application.

[0455] As shown in FIG. 24, the computing device 2400 includes a bus 2404, a processor 2401, a memory 2402 and a communication interface 2403. The processor 2401, the memory 2402 and the communication interface 2403 communicate with each other through the bus 2404.

[0456] The computing device 2400 can be a server or a terminal device. It should be understood that the number of processors and memories in the computing device 2400 is not limited in the present application.

[0457] It can be understood that the structural description of the computing device 2400 in the embodiments of the present application does not constitute a specific limitation on the computing device 2400. In other embodiments of the present application, the computing device 2400 can include other components in addition to the processor 2401 and the memory 2402.

[0458] The bus 2404 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one line is represented in FIG. 24, but it does not mean that there is only one bus or only one type of bus. The bus 2404 can include a path for transmitting information between various components (e.g., the memory 2402, the processor 2401, the communication interface 2403) of the computing device 2400.

[0459] The processor 2401 can include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP), etc.

[0460] The processor 2401 can be a system on a chip (SOC), and the processor 2401 can include a central processing unit (CPU) and can further include other types of processors.

[0461] The processor 2401 can include a CPU, a DSP, a microcontroller, or a digital signal processor, and can further include a GPU, an embedded neural network processing unit (NPU), and an image signal processor (ISP), and can further include necessary hardware accelerators or logic processing hardware circuits such as ASIC, or one or more integrated circuits for controlling the program execution of the technical solutions of the present application, etc. In addition, the processor can have the function of operating one or more software programs, and the software programs can be stored in a storage medium.

[0462] The processor 2401 can include one or more processing units. For example, the processor can include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units can be independent components or integrated in one or more processors. In some embodiments, the computing device 2400 can also include one or more processors 2401. Among them, the controller can generate operation control signals according to instruction operation codes and timing signals to complete the control of fetching and executing instructions.

[0463] In some embodiments, the processor 2401 can include one or more interfaces. The interface can include an inter-integrated circuit (I2C) interface, an integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM card interface, and / or a USB interface, etc. Among them, the USB interface is an interface conforming to the USB standard specification, which can be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface can be used to connect a charger to charge the computing device, or to transmit data between the computing device and the peripheral device.

[0464] The memory 2402 can include volatile memory (e.g., random access memory (RAM)). The processor 2401 can also include non-volatile memory (e.g., read-only memory (ROM), flash memory, a hard disk drive (HDD), or a solid-state drive (SSD)).

[0465] The memory 2402 stores executable program code, and the processor 2401 executes the executable program code to respectively implement the functions of the aforementioned image acquisition module 110, the virtual clothes matching module 130, the virtual human body configuration module 140, the try-on module 150, and the display module 160, so as to implement the clothes try-on method proposed in the embodiments of the present application. That is, the memory 2402 stores instructions for executing the clothes try-on method proposed in the embodiments of the present application.

[0466] The memory 2402 can include a code storage area and a data storage area. The code storage area can store an operating system. The data storage area can store data created during use of the computing device 2400, and the like. In addition, the memory 2402 can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more disk storage components, flash memory components, universal flash storage (UFS), and the like.

[0467] The memory 2402 can be a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions, and can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magneto-optical disk storage (including a compact disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, and the like), a magnetic disk storage medium or other magnetic storage device, or can also be any computer readable medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer.

[0468] The processor 2401 and the memory 2402 can be combined into one processing device, more commonly, they are independent components from each other.

[0469] The communication interface 2403 uses a transceiving module such as but not limited to a network interface card, a transceiver, to realize the communication between the computing device 2400 and other devices or communication networks.

[0470] The computing device 2400 can also include an external memory interface for connecting an external memory card such as a Micro SD card to extend the storage capacity of the computing device. The external memory card communicates with the processor 2401 through the external memory interface to realize the data storage function. For example, files such as music, video, etc. are saved in the external memory card.

[0471] In another embodiment, the clothes fitting device provided by the present application can be implemented on multiple computing devices. For example, the clothes fitting device provided by the present application is implemented by a terminal device including a display device and an image acquisition device, and a cloud server connected to the terminal device.

[0472] An embodiment of the present application further provides a computing device cluster. The computing device cluster includes at least one computing device, each computing device including a memory and a processor; the processor of at least one computing device in the computing device cluster is configured to execute instructions stored in the memory of at least one computing device in the computing device cluster, so that the computing device cluster performs the method as described in the embodiments of the present application.

[0473] For example, in an embodiment, the computing device cluster includes a first computing device (for example, a mobile phone, AR glasses) and a second computing device (for example, a cloud server).

[0474] Specifically, the first computing device and the second computing device can refer to the structure shown in FIG. 24. In an embodiment, the first computing device is configured to implement the functions of the image acquisition module 110 and the display module 160 of the clothes fitting device shown in FIG. 2. The second computing device is configured to implement the functions of the virtual clothes matching module 130, the virtual human body structure module 140, and the fitting module 150 of the clothes fitting device shown in FIG. 2.

[0475] FIG. 25 is a schematic diagram of a computing device cluster according to an embodiment of the present application.

[0476] As shown in FIG. 25, the computing device cluster includes at least one computing device 2500 (the structure of the computing device 2500 can refer to the computing device 2400). The computing device 2500 can be a server or a terminal device. Each computing device 2500 includes a bus 2504 (refer to the bus 2404), a processor 2501 (refer to the processor 2401), a memory 2502 (refer to the memory 2402), and a communication interface 2503 (refer to the communication interface 2403).

[0477] The memory 2501 in one or more computing devices in the computing device cluster can store the same instructions for performing the clothes fitting method proposed in the embodiments of the present application.

[0478] In some possible implementation manners, the memory 2501 of one or more computing devices 2500 in the computing device cluster can also respectively store partial instructions for performing the clothes fitting method proposed in the embodiments of the present application. In other words, the combination of one or more computing devices 2500 can collectively execute the instructions for performing the method proposed in the embodiments of the present application.

[0479] It should be noted that the memory 2501 in different computing devices 2500 in the computing device cluster can store different instructions, respectively used for performing partial functions of the model training apparatus proposed in the embodiments of the present application. That is, the instructions stored in the memory 2502 in different computing devices 2500 can implement the functions of one or more of the image acquisition module 110, the virtual clothes matching module 130, the virtual human body construction module 140, the fitting module 150, and the display module 160.

[0480] In some possible implementation manners, one or more computing devices in the computing device cluster can be connected through a network. The network can be a wide area network or a local area network, etc.

[0481] FIG. 26 is a schematic diagram of network connection of a computing device cluster according to an embodiment of the present application.

[0482] As shown in FIG. 26, two computing devices 2600A and 2600B are connected through a network. Specifically, the communication interface in each computing device is connected with the network. The structures of the computing devices 2600A and 2600B can refer to the computing device 2400.

[0483] The computing device 2600A includes a bus 2604A (refer to the bus 2404), a processor 2601A (refer to the processor 2401), a memory 2602A (refer to the memory 2402), and a communication interface 2603A (refer to the communication interface 2403).

[0484] The computing device 2600B includes a bus 2604B (cf. bus 2404), a processor 2601B (cf. processor 2401), a memory 2602B (cf. memory 2402), and a communication interface 2603B (cf. communication interface 2403).

[0485] In an embodiment, the computing device 2600A is a terminal device and the computing device 2600B is a server.

[0486] It should be understood that the functions of the computing device 2600A shown in FIG. 26 can also be completed by multiple computing devices. Likewise, the functions of the computing device 2600B can also be completed by multiple computing devices.

[0487] An embodiment of the present application also provides an electronic chip. The electronic chip is used to execute the method processes or part of the method processes described in the embodiments of the present application.

[0488] Specifically, the electronic chip includes a processor for executing program instructions, when the computer program instructions are executed by the processor, triggering the electronic chip to execute the method steps as described in the embodiments of the present application. The processor of the electronic chip can refer to the processor of the computing device described above.

[0489] The devices, apparatuses, and modules illustrated in the embodiments of the present application can be specifically implemented by computer chips or entities, or by products with certain functions.

[0490] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, device, or computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media having computer-usable program code contained therein.

[0491] In several embodiments provided by the present application, any function if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts of the technical solutions that make contributions to the prior art, or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0492] Specifically, an embodiment of the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program causes a computer to execute the method provided by the embodiment of the present application when the computer program is run on the computer.

[0493] An embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program causes a computer to execute the method provided by the embodiment of the present application when the computer program is run on the computer.

[0494] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the method, device (apparatus) and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and a combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device implemented in the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0495] These computer program instructions can also be stored in a computer readable storage medium, which can direct a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a manufactured product including an instruction device, which implements the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0496] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable data processing devices to generate a computer implemented process, so that the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0497] It should also be noted that, in the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent the cases of A alone, A and B together, and B alone. Wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0498] In the embodiments of the present application, the terms "comprise", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or device. Without more limitations, the element defined by the sentence "comprises a" does not exclude the existence of another same element in the process, method, article or device including the element.

[0499] The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types. The present application can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0500] Each embodiment in the present application is described in a progressive manner, and the same and similar parts of each embodiment can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0501] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments of the present application can be realized by electronic hardware, computer software and combination of electronic hardware and computer software. Whether the functions are realized in hardware or software mode depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to realize the described functions, but such implementation should not be considered beyond the scope of the present application.

[0502] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described devices, apparatuses and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0503] The above describes only specific embodiments of the present application, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. The protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of fitting a garment, characterized by, The method comprises: acquiring at least one image of a real garment; performing matching retrieval in a plurality of virtual garment models according to the at least one image of the real garment, acquiring a retrieval result, and obtaining a try-on garment model according to the retrieval result; acquiring a virtual human body model; combining the virtual human body model and the try-on garment model to obtain a virtual wearing model, the virtual wearing model being a model of a virtual human body wearing a virtual garment; performing image rendering based on the virtual wearing model to generate a virtual character image wearing a virtual garment.

2. The method of claim 1, wherein, The matching retrieval in the plurality of virtual garment models according to the at least one image of the real garment, the acquisition of the retrieval result, and the obtaining of the try-on garment model according to the retrieval result comprise: retrieving one or more first virtual garment models from the plurality of virtual garment models, the one or more first virtual garment models having a matching degree with the at least one image of the real garment exceeding a first preset value; obtaining the try-on garment model according to the one or more first virtual garment models.

3. The method of claim 2, wherein, The retrieval of the one or more first virtual garment models from the plurality of virtual garment models having a matching degree with the image data exceeding a preset value comprises: inputting the at least one image of the real garment into a neural network model to obtain the one or more first virtual garment models.

4. The method according to claim 2 or 3, characterized in that, The obtaining of the try-on garment model according to the one or more first virtual garment models comprises: taking a first virtual garment model having a highest matching degree with the at least one image of the real garment from the one or more first virtual garment models as the try-on garment model.

5. The method according to claim 2 or 3, characterized in that, The obtaining of the try-on garment model according to the one or more first virtual garment models comprises: providing a virtual garment selection page, the virtual garment selection page being used to display one or more virtual garment images respectively corresponding to the one or more first virtual garment models; receiving a selection instruction of a user, the selection instruction being used to indicate a virtual garment image selected by the user from the one or more virtual garment images; taking a first virtual garment model corresponding to the virtual garment image selected by the user as the try-on garment model.

6. The method according to any one of claims 2-5, characterized in that, The matching retrieval in the plurality of virtual garment models according to the at least one image of the real garment, the acquisition of the retrieval result, and the obtaining of the try-on garment model according to the retrieval result further comprise: when the one or more first virtual garment models are not retrieved, retrieving one or more second virtual garment models from the plurality of virtual garment models, the one or more second virtual garment models having a matching degree of a garment style with the at least one image of the real garment exceeding a second preset value, and retrieving one or more third virtual garment models from the plurality of virtual garment models, the one or more third virtual garment models having a matching degree of a garment color with the at least one image of the real garment exceeding a third preset value. generate one or more fourth virtual clothes models according to the one or more second virtual clothes models and the one or more third virtual clothes models, wherein a clothes style of the one or more fourth virtual clothes models matches the one or more second virtual clothes models, and a clothes color of the one or more fourth virtual clothes models matches the one or more third virtual clothes models; obtain the try-on clothes model according to the one or more fourth virtual clothes models.

7. The method according to any one of claims 1 to 6, characterized in that, combine the virtual human model and the try-on clothes model to obtain a virtual wearing model, including: obtain a virtual clothes model matched with the try-on clothes model from the plurality of virtual clothes models; combine the virtual human model, the try-on clothes model, and the virtual clothes model matched with the try-on clothes model to obtain the virtual wearing model.

8. The method of claim 7, wherein, The method further includes: configure a body action of the virtual character image, and / or configure a display scene of the virtual character image.

10. The method of claim 9, wherein: the combining the virtual human model and the try-on clothes model to obtain a virtual wearing model includes performing a first simulation process according to the virtual human model and the try-on clothes model to generate the virtual wearing model; 9. The method according to any one of claims 1-8, characterized in that, the configuring a body action of the virtual character image, and / or configuring a display scene of the virtual character image includes performing a second simulation process according to configuration information of the body action and / or configuration information of the display scene and the virtual wearing model. The device includes: an image acquisition module configured to acquire at least one image of a real clothes; a virtual clothes matching module configured to perform matching retrieval in a plurality of virtual clothes models according to the at least one image of the real clothes, obtain a retrieval result, and obtain a try-on clothes model according to the retrieval result; a virtual human construction module configured to obtain a virtual human model; 11. A garment fitting device, characterized by, a try-on module configured to combine the virtual human model and the try-on clothes model to obtain a virtual wearing model, the virtual wearing model being a model of a virtual human wearing virtual clothes; a display module configured to perform image rendering based on the virtual wearing model to generate a virtual character image wearing virtual clothes. The virtual clothes matching module is configured to: retrieve one or more first virtual clothes models having a matching degree with the at least one image of the real clothes exceeding a first preset value from the plurality of virtual clothes models; obtain the try-on clothes model according to the one or more first virtual clothes models. ​ 12. The apparatus of claim 11, wherein, ​ ​ ​ 13. The apparatus of claim 12, wherein, The virtual clothes matching module is configured to: input the image of the at least one real clothes into a neural network model to obtain the one or more first virtual clothes models.

14. The apparatus of claim 12 or 13, wherein, The virtual clothes matching module is configured to: select, as the try-on clothes model, the first virtual clothes model that has the highest matching degree with the image of the at least one real clothes from the one or more first virtual clothes models.

15. The apparatus of claim 12 or 13, wherein: The display module is configured to provide a virtual clothes selection page, the virtual clothes selection page being used to display one or more virtual clothes images corresponding to the one or more first virtual clothes models respectively; The virtual clothes matching module is configured to: receive a selection instruction of a user, the selection instruction being used to indicate a virtual clothes image selected by the user from the one or more virtual clothes images; and select, as the try-on clothes model, the first virtual clothes model corresponding to the virtual clothes image selected by the user.

16. The apparatus of any one of claims 12-15, wherein, The virtual clothes matching module is further configured to: when the one or more first virtual clothes models are not retrieved, retrieve, from the plurality of virtual clothes models, one or more second virtual clothes models that have a clothes style matching degree with the image of the at least one real clothes exceeding a second preset value, and retrieve one or more third virtual clothes models that have a clothes color matching degree with the image of the at least one real clothes exceeding a third preset value; generate one or more fourth virtual clothes models according to the one or more second virtual clothes models and the one or more third virtual clothes models, wherein the one or more fourth virtual clothes models have a clothes style matching the one or more second virtual clothes models, and the one or more fourth virtual clothes models have a clothes color matching the one or more third virtual clothes models; obtain the try-on clothes model according to the one or more fourth virtual clothes models.

17. The apparatus of any one of claims 11-16, wherein, The try-on module is configured to: obtain, from the plurality of virtual clothes models, a virtual clothes model that matches the try-on clothes model; combine the virtual human body model, the try-on clothes model, and the virtual clothes model that matches the try-on clothes model to obtain the virtual wearing model.

18. The apparatus of claim 17, wherein, The try-on module is configured to: obtain clothes features corresponding to the try-on clothes model, the clothes features including clothes type and / or clothes color; determine clothes features that match the try-on clothes model according to the clothes features corresponding to the try-on clothes model; obtain a virtual clothes model that matches the try-on clothes model based on the clothes features that match the try-on clothes model.

19. The apparatus of any one of claims 11-18, wherein, The display module is further configured to: configure a body action of the virtual character image, and / or configure a display scene of the virtual character image.

20. The apparatus of claim 19, wherein: The try-on module is configured to execute a first simulation process according to the virtual human body model and the try-on clothes model to generate the virtual wearing model; The display module is further configured to perform a second simulation process according to configuration information of the body action and / or configuration information of the display scene, and the virtual wearing model.

21. A cluster of computing devices, characterized in that, The computing device cluster includes at least one computing device, each computing device including a memory and a processor; The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device to cause the computing device cluster to perform the method of any one of claims 1-10.

22. A computer program product comprising instructions, characterized in that, The instructions, when executed by the computing device system, cause the computing device cluster to perform the method of any one of claims 1-10.

23. A computer-readable storage medium, characterized in that, Computer program instructions, when executed by a computer system, cause the computer system to perform the method of any one of claims 1-10.

Images