Method, device and equipment for customizing virtual clothes and medium

Abstract

The invention provides a method, a device, equipment and a medium for customizing virtual clothes. In one method, a customization request specifying a pattern to be added to a virtual garment to be customized is obtained. Based on the customization request, a pattern to be added to the virtual garment is generated using a generative model. A customized garment image that customizes the virtual garment is generated based on the pattern and the garment image of the virtual garment. By utilizing the exemplary implementation mode of the invention, a common user without costume design knowledge can be allowed to use the machine learning model to complete a relatively complex costume customization process by means of the rapid design capability of the machine learning model.

Description

Technical Field

[0001] Exemplary implementations of the present disclosure generally relate to the field of machine learning, and more particularly to methods, devices, apparatuses, and computer-readable storage media for customizing virtual clothing based on machine learning. Background Art

[0002] Machine learning technology has been widely used in many fields. For example, a technical solution has been proposed to use machine learning technology to assist clothing design. However, clothing design involves many aspects of knowledge and depends on the designer's inspiration and aesthetics. At this time, it is difficult for machine learning models to grasp the designer's creativity and thus fail to meet the designer's needs. At this time, it is expected that on the basis of existing styles of existing clothing, with the help of the rapid design capabilities of machine learning models, designers and / or ordinary users can complete a relatively simple clothing customization process. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for customizing a virtual garment is provided. In the method, a customization request is obtained, the customization request specifying a pattern to be added to the virtual garment to be customized. Based on the customization request, a generative model is used to generate the pattern to be added to the virtual garment. Based on the pattern and a garment image of the virtual garment, a customized garment image of the customized virtual garment is generated.

[0004] In a second aspect of the present disclosure, a device for customizing virtual clothing is provided. The device includes: an acquisition module configured to acquire a customization request, the customization request specifying a pattern to be added to the virtual clothing to be customized; a pattern generation module configured to generate a pattern to be added to the virtual clothing using a generation model based on the customization request; and an image generation module configured to generate a customized clothing image of the customized virtual clothing based on the pattern and the clothing image of the virtual clothing.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, and when the instructions are executed by the at least one processing unit, the electronic device executes the method according to the first aspect of the present disclosure.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor implements the method according to the first aspect of the present disclosure.

[0007] It should be understood that the content described in this content section is not intended to limit the key features or important features of the implementation of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In the following, in conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages and aspects of various implementations of the present disclosure will become more apparent. In the accompanying drawings, the same or similar figure labels represent the same or similar elements, wherein:

[0009] Figure 1 An application environment according to an exemplary implementation of the present disclosure is shown;

[0010] Figure 2 A process for customizing a virtual garment according to some implementations of the present disclosure is shown;

[0011] Figure 3 shows the architecture of a generative model according to some implementations of the present disclosure;

[0012] Figure 4 An interactive process for starting a custom virtual clothing function according to some implementations of the present disclosure is shown;

[0013] Figure 5 An interactive process for selecting a base style of a virtual garment according to some implementations of the present disclosure is shown;

[0014] Figure 6 An interactive process for inputting a customization request according to some implementations of the present disclosure is shown;

[0015] Figure 7 An interactive process for selecting a candidate pattern according to some implementations of the present disclosure is shown;

[0016] Figure 8 An interactive process for setting placement parameters according to some implementations of the present disclosure is shown;

[0017] Fig. 9 An interactive process for importing a user image according to some implementations of the present disclosure is shown;

[0018] Fig.10 An interactive process for presenting a try-on effect according to some implementations of the present disclosure is shown;

[0019] Fig.11 A flow chart showing a method for customizing a virtual garment according to some implementations of the present disclosure is shown;

[0020] Fig.12A block diagram showing an apparatus for customizing virtual clothing according to some implementations of the present disclosure; and

[0021] Fig.13 A block diagram of a device capable of implementing multiple implementations of the present disclosure is shown. DETAILED DESCRIPTION

[0022] The implementation of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain implementations of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be interpreted as being limited to the implementations described herein. On the contrary, these implementations are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and implementations of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0023] In the description of the implementation methods of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "an implementation" or "the implementation" should be understood as "at least one implementation". The term "some implementations" should be understood as "at least some implementations". The following may also include other explicit and implicit definitions. As used herein, the term "model" can represent the association relationship between various data. For example, the above-mentioned association relationship can be obtained based on a variety of technical solutions currently known and / or to be developed in the future.

[0024] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0025] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0026] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0027] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information is sent to the user in a manner such as a pop-up window, in which the prompt information can be presented in text form. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0028] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0029] The term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is satisfied. It will be understood that the timing of executing a subsequent action executed in response to the event or condition is not necessarily strongly related to the time when the event occurs or the condition is satisfied. For example, in some cases, the subsequent action may be executed immediately when the event occurs or the condition is satisfied; while in other cases, the subsequent action may be executed some time after the event occurs or the condition is satisfied.

[0030] Example Environment

[0031] Figure 1 FIG. 1 shows an application environment 100 according to an exemplary implementation of the present disclosure. Figure 1 As shown, user 110 can design clothing 130 via clothing design tool 120. Here, clothing design tool 120 can provide professional designers with multiple functions. For example, fabrics and colors can be selected for clothing, details such as collars and sleeves of clothing can be designed, and cloth cutting diagrams and three-dimensional effects of clothing can be provided, etc.

[0032] Although machine learning technology can be used to assist in the technical solution of clothing design, machine learning models are difficult to meet the needs of designers. At this time, it is hoped that a method can be provided based on the basic styles of existing clothing, with the help of the rapid design capabilities of machine learning models, to assist ordinary users in completing a relatively simple clothing customization process.

[0033] Overview of Customizing Virtual Clothing

[0034] In order to at least partially address the deficiencies in the prior art, according to an exemplary implementation of the present disclosure, a method for customizing virtual clothing is proposed. Figure 2 Describes an overview of an exemplary implementation according to the present disclosure, Figure 2 A process 200 for customizing a virtual garment according to some implementations of the present disclosure is shown. Figure 2As shown, a pattern 230 may be added to a base style of virtual garment 240 to generate a customized virtual garment, for example, a customized garment image 250 may be presented to a user.

[0035] In the virtual clothing customization process, a generation model 220 constructed using machine learning technology can be obtained to generate the pattern 230 with the help of the ability of machine learning technology. Specifically, a customization request 210 can be obtained from a user (e.g., a designer or an ordinary user other than a designer), and the customization request 210 can specify the pattern 230 to be added to the virtual clothing to be customized. As shown in the figure, the customization request 210 may include image data 212 or text data 214. Alternatively and / or additionally, the customization request 210 may include both the image data 212 and the text data 214.

[0036] The customization request 210 may be input as a prompt word into the generation model 220, so that the generation model 220 is used to generate the pattern 230 to be added to the virtual garment. It should be understood that the generation model 220 may be a pre-trained machine model and describes the association relationship between the customization request 210 and the pattern 230. Further, based on the pattern 230 and the garment image of the virtual garment, a customized garment image of the customized virtual garment may be generated.

[0037] By using the example implementation of the present disclosure, the powerful processing capability of the machine learning model can be used to generate a pattern 230 that matches the customization request 210, and then the pattern 230 can be used to achieve the purpose of customizing virtual clothing. In this way, even ordinary users who are not good at drawing and design can give full play to their creativity and customize virtual clothing that meets their needs.

[0038] The detailed process of customizing virtual clothing

[0039] Having described an overview of the techniques for customizing virtual clothing, in the following, reference will be made to Figure 3 An overview of the generation model 220 is described. Figure 3 4 shows an architecture 400 of a generation model according to some implementations of the present disclosure. Figure 3 As shown, the generation model 220 can be implemented based on various network structures currently known and / or to be developed in the future, and is used to describe the association relationship between the image data 310 and / or text data 311 in the customization request and the generated pattern 320 .

[0040] During the training process of the generative model 220, the training data may include the image data 310 and / or the text data 311, and include a true value image matching the image data 310 and / or the text data. The generative model 220 may be continuously updated in an iterative manner using a large amount of training data until the generative model 220 can grasp the association relationship between the image data 310 and / or the text data 311 and the generated pattern 320.

[0041] According to an example implementation of the present disclosure, the true value data of existing clothing of a certain brand can be used to train the generation model 220. For example, different generation models 220 can be trained for different brands, so that the customized virtual clothing can be more in line with the design concept of the brand.

[0042] According to an example implementation of the present disclosure, the generation model 220 may further consider other factors, for example, a pattern 320 having a style 312 may be generated based on a style 312 specified by a user, a pattern 320 matching the clothing attribute 313 may be generated based on a clothing attribute 313, a pattern 320 matching the processing technology 313 may be generated based on a processing technology 313 specified by a user, etc. In the following, more details of the generation model 220 will be described in conjunction with subsequent figures.

[0043] Figure 4 An interactive process 400 for initiating a custom virtual clothing function according to some implementations of the present disclosure is shown. Figure 4 As shown, the user can start the custom virtual clothing function in the interactive interface 410. The "creative studio" is shown at the top of the interactive interface 410, and the user can click button 420 to start the custom virtual clothing function to enter the subsequent interactive interface for customizing virtual clothing. The "activity space" is shown at the bottom of the interactive interface 410, and the user can click button 430 to enter the interactive interface for displaying customized virtual clothing to browse virtual clothing customized by the user himself and / or other users.

[0044] After the user clicks button 420, the Figure 5 The interactive interface 510 shown in FIG. Figure 5 An interactive process 500 for selecting a base style for a virtual garment according to some implementations of the present disclosure is shown. Figure 5As shown, an interactive interface 510 for specifying virtual clothing may be provided, and the interactive page 510 may include basic styles of virtual clothing that may be processed, such as T-shirts, polo shirts, jeans, dresses, etc. A user interaction 520 between a user and the interactive interface 510 may be detected, and if a user interaction 520 for the interactive interface is received, the virtual clothing corresponding to the user interaction 520 may be used as the virtual clothing to be processed.

[0045] After the user has selected the basic style of the virtual garment through user interaction 520, the following may be presented: Figure 6 The interactive page 610 shown in FIG. Figure 6 An interactive process 600 for inputting a customization request according to some implementations of the present disclosure is shown. According to an example implementation of the present disclosure, an interactive interface for specifying image data may be provided; alternatively and / or additionally, an interactive interface for specifying text data may be provided. Specifically, Figure 6 The illustrated interactive interface 610 may include an image box 620 for specifying image data, and a text box 630 for specifying text data.

[0046] According to an example implementation of the present disclosure, when a user interaction with an interactive interface is received, image data corresponding to the user interaction can be obtained. The user interaction includes at least one of the following: a user interaction for drawing image data, and a user interaction for importing image data. In other words, the user is allowed to specify image data in a variety of ways. For example, the user can click on the brush tool 622 to manually draw an image, or click on the import tool 624 to import an image locally on the client device and / or at other locations in the network.

[0047] Further, the user can describe the requirements of the desired pattern to be generated in natural language in the text box 630. For example, the user can specify the content, color, and shape of the image, etc. Alternatively and / or additionally, the user is allowed to specify that text is included in the generated image. For example, the text box 630 can be input: "Add the text 'good morning' to the image", and the generated image can include the text "good morning".

[0048] According to an example implementation of the present disclosure, the user may specify a customization request in either the image box 620 or the text box 630. Then, the user may press the generate button 640 to generate one or more patterns. In the process of generating the pattern, the image data in the image box 620 and the text data in the text box 630 will be input to the respective Figure 3 The generation model 220 in the image data 310 and the input terminals of the text data 311 correspond to each other. At this time, the generated pattern will include the content specified by the customization request.

[0049] According to an exemplary implementation of the present disclosure, an interactive interface for specifying the style of a pattern may be further provided. Specifically, Figure 6 The upper part of the interactive interface 610 in the example may include a plurality of predetermined styles, for example, a mosaic 612 style, an abstract 614 style, and a punk 616 style, etc. When a user interaction for any of the above styles is received, a pattern may be generated using a generation model based on the style corresponding to the user interaction.

[0050] During the pattern generation process, the specified style will be input to Figure 3 The input end corresponding to the style 312 in the generation model 220 in the example is used, and the difference between the generated pattern prediction and the true value pattern is used as the loss function. The generated pattern will conform to the specified style. For example, when the user selects the mosaic 612 style, a pattern represented by a mosaic can be generated. Using the example implementation of the present disclosure, the user is allowed to define various aspects of the pattern in a more sophisticated way, so that the generated pattern is more in line with the user's needs.

[0051] According to an example implementation of the present disclosure, clothing attributes associated with virtual clothing can be further determined in the process of generating a pattern. Here, clothing attributes can include but are not limited to at least one of the following: clothing style, clothing color, clothing material, and clothing type, etc. Further, the pattern can be generated using a generation model based on clothing attributes. At this time, the generation model 220 can further describe the association relationship between clothing attributes and the generated pattern. For example, clothing attributes can be further considered in the process of selecting training data. Corresponding training data can be selected according to different clothing styles, clothing colors, clothing materials, and clothing types, so that the generation model 220 can generate a pattern suitable for the clothing attribute.

[0052] Specifically, for a black cotton casual T-shirt, the training data may include a large-scale abstract pattern in dark tones; for a light-colored tight-fitting dress, the ground truth image may include a small-scale pattern in light tones, and so on. In the generation process, the user-specified clothing attributes may be input into the corresponding Figure 3 The input end of the clothing attribute 313 is input, and the difference between the generated pattern prediction and the true value pattern is used as the loss function. At this time, the generated pattern will conform to the clothing attribute. In this way, more assistance can be provided to ordinary users who lack clothing design knowledge. Thus, without user intervention, the coordination between clothing attributes and patterns is fully considered, and a pattern that better matches the virtual clothing is generated.

[0053] According to an example implementation of the present disclosure, in the process of generating a pattern, the processing technology of the virtual clothing can be further considered. For example, an interactive interface for specifying the processing technology of adding a pattern to the virtual clothing can be provided, and the processing technology can include but is not limited to at least one of the following: screen printing process, spraying process, transfer process, and embroidery process, etc. In the case of receiving a user interaction with the interactive interface, the pattern can be generated using the generation model based on the processing technology corresponding to the user interaction.

[0054] According to an example implementation of the present disclosure, the processing technology can be manually selected by the user, or the appropriate processing technology can be automatically selected based on the clothing attributes. For example, the spraying process can be selected for a cotton T-shirt, and the embroidery process can be selected for a silk dress, etc. At this time, the processing technology can be further considered in the process of selecting training data. For example, corresponding training data can be selected according to different processing technologies, so that the generation model 220 can generate a pattern suitable for the processing technology.

[0055] During the generation process, user-specified and / or automatically determined processing techniques can be input to the corresponding Figure 3 The processing technology 314 is input to the input terminal, and the difference between the generated pattern prediction and the true value pattern is used as the loss function. At this time, the generated pattern will meet the processing technology of the virtual clothing. In this way, more assistance can be provided to ordinary users who lack clothing design knowledge, and the coordination between the processing technology and the pattern can be fully considered, so as to generate a pattern that better matches the virtual clothing.

[0056] According to an exemplary implementation of the present disclosure, a plurality of candidate patterns may be provided so that the user can select a desired pattern. Figure 7 An interactive process 700 for selecting a candidate pattern according to some implementations of the present disclosure is shown. Figure 7 As shown, the interactive interface 710 may include multiple candidate patterns 712, 714, 716, and 718, etc. The user may interact with each candidate pattern in the interactive interface 710. When a selection of a target pattern among the multiple candidate patterns is received, a customized clothing image may be generated based on the selected target pattern and the clothing image.

[0057] For example, the user can select a candidate pattern 716 and press button 722 to enter the subsequent step. Alternatively and / or additionally, if the user is not satisfied with the current plurality of candidate patterns, the user can press button 720 to return to the previous interactive interface to modify the customization request. In this way, more choices can be provided to the user, thereby providing a richer virtual clothing customization process.

[0058] According to an exemplary implementation of the present disclosure, in the process of generating a customized clothing image, an interactive interface for specifying placement parameters of a pattern in a virtual clothing may be further provided. For example, after the user presses button 722, an interactive interface may be provided such as Figure 8 The interactive interface shown. Figure 8 An interactive process 800 for setting placement parameters according to some implementations of the present disclosure is shown. Figure 8 As shown, the placement parameters include at least any one of the following: position, size, direction, and the like.

[0059] Specifically, the user can place the generated pattern in the middle, left, or right position of the virtual clothing; alternatively and / or additionally, the user can drag the pattern and place the pattern in a suitable position. The user can set the size of the pattern, for example, large, medium, or small size can be set; alternatively and / or additionally, the user can drag the border of the pattern to adjust the size, etc. The user can set the rotation direction of the pattern, and set to add the generated original pattern to the virtual clothing, or add the image after "cutout processing" to the virtual clothing, etc. In the case of receiving a user interaction with the interactive interface 810, the pattern is added based on the placement parameters corresponding to the user interaction. In this way, the user can be allowed to control the pattern placement in a more flexible way, so as to obtain a customized virtual clothing that better meets the user's needs.

[0060] According to an example implementation of the present disclosure, when a customized virtual garment has been generated, a fitting effect can be further provided to the user. Specifically, a user image for specifying a fitting character for fitting the customized virtual garment can be received, and a fitting effect image of the customized virtual garment can be generated based on the user image and the customized garment image. In this way, more abundant information about the customized virtual garment can be provided to the user, thereby assisting the user in designing a virtual garment that better meets their needs.

[0061] According to an example implementation of the present disclosure, an auxiliary design page may be further provided to the user. For example, corresponding clothing information may be queried from a clothing database based on the user's selection of a basic style. For example, a variety of candidate items may be provided to the user based on the queried information and on predetermined rules. Here, the rules may describe the clothing information and the relevant features of the pattern applicable to this type of clothing. For example, if the basic style is a cotton T-shirt, the user may be recommended to select an abstract style image, use a spraying process, place the pattern in the middle, and so on. For another example, if the basic style is a silk dress, the user may be recommended to select a fine brushwork style, use an embroidery process, and place the pattern in the corner of the clothing, and so on.

[0062] By using the example implementation of the present disclosure, it is possible to add rules (e.g., rules summarized by experienced designers) to the design tool to guide ordinary users to complete the customization process of virtual clothing. In this way, ordinary users can give full play to their personal abilities to design better works while complying with the basic rules of clothing design.

[0063] Fig. 9 FIG. 9 shows an interactive process 900 for importing user images according to some implementations of the present disclosure. Fig. 9 As shown, an interactive interface 910 may be provided, which may include a model image 920, and the model image includes a fitting effect of a model trying on a customized virtual garment. Further, the user may import a user image 930 including himself or another person, and then click a button 940 to generate a corresponding fitting effect. It should be understood that although Fig. 9 The illustrated user image 930 includes only a facial image, alternatively and / or additionally, the user image 930 may include only a facial image, or may include a full-body image.

[0064] Fig.10 FIG. 1 shows an interactive process 1000 for presenting a try-on effect according to some implementations of the present disclosure. Fig.10 As shown, in the interactive interface 1010, a fitting effect 1020 can be generated based on a model image 920 and a user image 930 of a customized virtual garment. Specifically, a facial image in the user image can be identified, and if it is determined that the facial image satisfies a first predetermined condition (e.g., higher than a predetermined resolution, or the uploaded image only includes a facial part, etc.), a fusion model can be called to replace the model face in the model image with the facial image to generate a fitting effect image. It should be understood that the fusion model can be a pre-trained machine learning model that can replace the model face in the model image with the facial image uploaded by the user, thereby generating a fitting effect 1020.

[0065] According to an example implementation of the present disclosure, a torso image in a user image can be identified. If it is determined that the torso image satisfies a second predetermined condition (e.g., includes a complete torso portion, or includes a relevant torso portion of a customized virtual garment), a fusion model can be called to replace the garment portion in the torso image with the customized garment image to generate a try-on effect image. It should be understood that the fusion model here can be a pre-trained machine learning model so as to replace the torso portion in the user image with the customized garment image. In this way, the user is allowed to obtain a full-body try-on effect by only uploading the avatar data.

[0066] It should be understood that, assuming that the user posture in the user image is different from the model posture in the model image, the visual effect of the customized virtual clothing can be adjusted and matched to the user posture. For example, in the process of training the fusion model, images including different postures can be used to perform training respectively so that the customized virtual clothing in the generated fitting effect can conform to the posture of the user image. In this way, the user is allowed to obtain the fitting effect in different postures, thereby facilitating the user to adjust the customization process. If the user is not satisfied with the fitting effect, the user can click button 1030 to return to the previous page to adjust the various customization parameters.

[0067] It should be understood that the virtual clothing try-on effect in the present disclosure is achieved in the application environment of clothing design. In the context of the present disclosure, selecting basic clothing styles, generating and adding patterns to virtual clothing to generate virtual clothing, and subsequently trying on the virtual clothing is a complete process to assist users in achieving clothing design goals. To this end, the present disclosure provides a complete set of auxiliary design tools to implement the virtual clothing customization function described above, in this way, ordinary users who do not have professional knowledge can be assisted in customizing their favorite clothing.

[0068] According to an exemplary implementation of the present disclosure, the virtual clothing customization function described above can be implemented in a separate application. Alternatively and / or additionally, the virtual clothing customization function can be embedded in a social network application. In this case, users of the social network application can call the virtual clothing customization function and publish their customized virtual clothing in the social network application. Fig.10 As shown, the interactive interface 1010 can provide a function for publishing customized virtual clothing, for example, the user can publish his own work by clicking button 1040. When a click on button 1040 is received, the customized virtual clothing can be published in the social network application.

[0069] According to an example implementation of the present disclosure, a user can publish a customized virtual garment in his / her own user account in a social networking application. For example, a social networking application can provide a personal space for each user account and allow the user to publish videos, short videos, texts, images and / or a combination thereof in the personal space. At this time, the user can publish the customized virtual garment in his / her personal space, and in this way, richer visual content can be provided.

[0070] According to an example implementation of the present disclosure, a user may publish customized virtual clothing in an activity space in a social networking application for providing virtual clothing customization. For example, a clothing producer may establish an official account in a social networking application and establish a dedicated activity space to provide virtual clothing customization services to a large number of users. Users may participate in activities and publish customized virtual clothing in corresponding activity spaces. In this way, customized virtual clothing for a large number of users may be obtained, and further activities such as voting may be held, voting information of each user may be obtained, and when the number of votes for a certain customized virtual clothing meets a predetermined condition, real clothing may be produced based on the customized virtual clothing, and so on.

[0071] By using the exemplary implementation of the present disclosure, ordinary users who do not have knowledge of clothing design can use machine learning models to complete a relatively complex virtual clothing customization process with the help of the rapid design capabilities of machine learning models. Furthermore, clothing manufacturers are allowed to effectively obtain user needs, thereby quickly completing the development process of new products.

[0072] Example Process

[0073] Fig.11 A flow chart of a method 1100 for customizing a virtual garment according to some implementations of the present disclosure is shown. At block 1110, a customization request is obtained, the customization request specifying a pattern to be added to a virtual garment to be customized; at block 1120, a pattern to be added to the virtual garment is generated using a generative model based on the customization request; and at block 1130, a customized garment image of the customized virtual garment is generated based on the pattern and the garment image of the virtual garment.

[0074] According to an example implementation of the present disclosure, the method 1100 further includes: providing an interactive interface for specifying virtual clothing; and in response to receiving a user interaction with the interactive interface, determining the virtual clothing corresponding to the user interaction.

[0075] According to an example implementation of the present disclosure, the customization request includes at least any one of image data and text data represented by a natural language.

[0076] According to an example implementation of the present disclosure, the customization request includes image data, and obtaining the image data includes: providing an interactive interface for specifying the image data; and in response to receiving a user interaction with the interactive interface, obtaining image data corresponding to the user interaction, the user interaction including at least any one of the following: user interaction for drawing the image data, and user interaction for importing the image data.

[0077] According to an example implementation of the present disclosure, generating a pattern further includes: providing an interactive interface for specifying a style of the pattern; and in response to receiving a user interaction with the interactive interface, generating the pattern using a generation model based on the style corresponding to the user interaction.

[0078] According to an example implementation of the present disclosure, generating a pattern further includes: determining clothing attributes associated with the virtual clothing, the clothing attributes including at least any one of the following: clothing style, clothing color, clothing material, clothing type; and generating a pattern using a generation model based on the clothing attributes.

[0079] According to an example implementation of the present disclosure, generating a pattern further includes: providing an interactive interface for specifying a processing technology for adding the pattern to a virtual garment, the processing technology including at least any one of the following: a screen printing process, a spraying process, a transfer process, and an embroidery process; and in response to receiving a user interaction with the interactive interface, generating the pattern using a generation model based on the processing technology corresponding to the user interaction.

[0080] According to an example implementation of the present disclosure, the pattern includes a plurality of candidate patterns, and generating the customized clothing image further includes: in response to receiving a selection of a target pattern from among the plurality of candidate patterns, generating the customized clothing image based on the target pattern and the clothing image.

[0081] According to an example implementation of the present disclosure, generating a customized clothing image further includes: providing an interactive interface for specifying placement parameters of a pattern in a virtual garment, the placement parameters including at least any of the following: position, size, direction; and in response to receiving a user interaction with the interactive interface, adding a pattern based on the placement parameters corresponding to the user interaction.

[0082] According to an example implementation of the present disclosure, the method 1100 further includes: receiving a user image for specifying a character trying on the customized virtual clothing; and generating a try-on effect image of the customized virtual clothing based on the user image and the customized clothing image.

[0083] According to an example implementation of the present disclosure, generating a fitting effect image includes: identifying a facial image in a user image; and in response to determining that the facial image satisfies a first predetermined condition, calling a fusion model to replace a model's face in a model image with the facial image to generate a fitting effect image, wherein the model image includes a fitting effect of a model trying on customized virtual clothing.

[0084] According to an example implementation of the present disclosure, generating a fitting effect image includes: identifying a torso image in a user image; and in response to determining that the torso image satisfies a second predetermined condition, calling a fusion model to replace a clothing part in the torso image with a customized clothing image to generate a fitting effect image.

[0085] According to an example implementation of the present disclosure, method 1100 is called in a social networking application, and method 1100 further includes: providing an interactive interface for publishing customized virtual clothing; and publishing the customized virtual clothing in the social networking application in response to receiving a user interaction with the interactive interface.

[0086] According to an example implementation of the present disclosure, publishing customized virtual clothing in a social networking application includes at least any of the following: publishing the customized virtual clothing in a user account of a user interacting in the social networking application; and publishing the customized virtual clothing in an activity space in the social networking application for providing virtual clothing customization.

[0087] Example devices and equipment

[0088] Fig.12 A block diagram of an apparatus 1200 for customizing virtual clothing according to some implementations of the present disclosure is shown. The apparatus includes: an acquisition module 1210 configured to acquire a customization request, the customization request specifying a pattern to be added to the virtual clothing to be customized; a pattern generation module 1220 configured to generate a pattern to be added to the virtual clothing using a generation model based on the customization request; and an image generation module 1230 configured to generate a customized clothing image of the customized virtual clothing based on the pattern and the clothing image of the virtual clothing.

[0089] According to an example implementation of the present disclosure, the apparatus 1200 further includes: a providing module configured to provide an interactive interface for specifying virtual clothing; and a virtual clothing determining module configured to determine, in response to receiving a user interaction with the interactive interface, a virtual clothing corresponding to the user interaction.

[0090] According to an exemplary implementation of the present disclosure, the customization request includes at least any one of image data and text data represented by a natural language.

[0091] According to an example implementation of the present disclosure, a customization request includes image data, and an acquisition module includes: a providing module configured to provide an interactive interface for specifying image data; and an image data acquisition module configured to, in response to receiving a user interaction with the interactive interface, acquire image data corresponding to the user interaction, the user interaction including at least any one of the following: user interaction for drawing image data, and user interaction for importing image data.

[0092] According to an example implementation of the present disclosure, the pattern generation module further includes: a providing module configured to provide an interactive interface for specifying the style of the pattern; and a style-based generation module configured to generate a pattern using a generation model based on a style corresponding to the user interaction in response to receiving a user interaction with the interactive interface.

[0093] According to an example implementation of the present disclosure, the pattern generation module further includes: a determination module, configured to determine clothing attributes associated with the virtual clothing, the clothing attributes including at least any one of the following: clothing style, clothing color, clothing material, clothing type; and an attribute-based generation module, configured to generate a pattern based on the clothing attributes using a generation model.

[0094] According to an example implementation of the present disclosure, the pattern generation module further includes: a providing module configured to provide an interactive interface for specifying a processing technology for adding a pattern to a virtual garment, the processing technology including at least any one of the following: a screen printing process, a spraying process, a transfer process, and an embroidery process; and a process-based generation module configured to generate a pattern using a generation model based on the processing technology corresponding to the user interaction in response to receiving a user interaction with the interactive interface.

[0095] According to an example implementation of the present disclosure, the pattern includes multiple candidate patterns, and the pattern generation module further includes: a selection-based generation module configured to generate a customized clothing image based on the target pattern and the clothing image in response to receiving a selection of a target pattern among the multiple candidate patterns.

[0096] According to an example implementation of the present disclosure, the pattern generation module further includes: a providing module configured to provide an interactive interface for specifying placement parameters of the pattern in the virtual garment, the placement parameters including at least any one of the following: position, size, direction; and a parameter-based generation module configured to, in response to receiving a user interaction with the interactive interface, add a pattern based on the placement parameters corresponding to the user interaction.

[0097] According to an example implementation of the present disclosure, the device 1200 further includes: a receiving module configured to receive a user image of a person trying on customized virtual clothing for specifying the person trying on the customized virtual clothing; and an effect generating module configured to generate a trying-on effect image of the customized virtual clothing based on the user image and the customized clothing image.

[0098] According to an example implementation of the present disclosure, an effect generation module includes: a first recognition module, configured to recognize a facial image in a user image; and a second fusion module, configured to, in response to determining that the facial image satisfies a first predetermined condition, call a fusion model to replace a model face in a model image with the facial image to generate a fitting effect image, wherein the model image includes a fitting effect of a model trying on customized virtual clothing.

[0099] According to an example implementation of the present disclosure, the effect generation module includes: a second recognition module, configured to recognize a torso image in a user image; and a second fusion module, configured to, in response to determining that the torso image satisfies a second predetermined condition, call a fusion model to replace a clothing part in the torso image with a customized clothing image to generate a try-on effect image.

[0100] According to an example implementation of the present disclosure, the device 1200 is implemented in a social networking application, and the device 1200 further includes: a providing module, configured to provide an interactive interface for publishing customized virtual clothing; and a publishing module, configured to publish the customized virtual clothing in the social networking application in response to receiving a user interaction with the interactive interface.

[0101] According to an example implementation of the present disclosure, the publishing module further includes: a first publishing module, configured to publish customized virtual clothing in a user account of a user interaction in a social networking application; and a second publishing module, configured to publish customized virtual clothing in an activity space in the social networking application for providing virtual clothing customization.

[0102] Fig.13 1 shows a block diagram of a device 1300 capable of implementing multiple implementations of the present disclosure. It should be understood that Fig.13 The computing device 1300 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the implementations described herein. Fig.13 The computing device 1300 shown may be used to implement the methods described above.

[0103] like Fig.13 As shown, computing device 1300 is in the form of a general-purpose computing device. Components of computing device 1300 may include, but are not limited to, one or more processors or processing units 1310, memory 1320, storage device 1330, one or more communication units 1340, one or more input devices 1350, and one or more output devices 1360. Processing unit 1310 may be an actual or virtual processor and is capable of performing various processes according to a program stored in memory 1320. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to increase the parallel processing capabilities of computing device 1300.

[0104] The computing device 1300 typically includes a plurality of computer storage media. Such media may be any available media accessible to the computing device 1300, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1320 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 1330 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data (e.g., training data for training) and may be accessed within the computing device 1300.

[0105] The computing device 1300 may further include additional removable / non-removable, volatile / non-volatile storage media. Fig.13 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. Memory 1320 may include a computer program product 1325 having one or more program modules that are configured to perform various methods or actions of various implementations of the present disclosure.

[0106] The communication unit 1340 enables communication with other computing devices via a communication medium. Additionally, the functions of the components of the computing device 1300 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Therefore, the computing device 1300 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0107] Input device 1350 may be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 1360 may be one or more output devices, such as a display, speaker, printer, etc. Computing device 1300 may also communicate with one or more external devices (not shown) through communication unit 1340 as needed, such as storage devices, display devices, etc., communicate with one or more devices that allow a user to interact with computing device 1300, or communicate with any device that allows computing device 1300 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0108] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, the computer program product is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is provided, on which a computer program is stored, and when the program is executed by a processor, the method described above is implemented.

[0109] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0110] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0111] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0112] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0113] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for customizing virtual clothing, comprising: obtaining a customization request specifying a pattern to be added to a virtual garment to be customized; generating the pattern to be added to the virtual garment using a generative model based on the customization request; as well as Based on the pattern and the garment image of the virtual garment, a customized garment image of the customized virtual garment is generated.

2. The method according to claim 1, further comprising: Providing an interactive interface for specifying the virtual clothing; as well as In response to receiving a user interaction with the interactive interface, the virtual garment corresponding to the user interaction is determined. 3 . The method according to claim 1 , wherein the customization request includes at least any one of image data and text data expressed using a natural language.

4. The method of claim 1 , wherein the customization request includes image data, and obtaining the image data comprises: providing an interactive interface for specifying the image data; as well as In response to receiving a user interaction for the interactive interface, the image data corresponding to the user interaction is acquired, wherein the user interaction includes at least any one of the following: a user interaction for drawing the image data, and a user interaction for importing the image data.

5. The method of claim 1 , wherein generating the pattern further comprises: Providing an interactive interface for specifying the style of the pattern; as well as In response to receiving a user interaction with the interactive interface, the pattern is generated using the generative model based on a style corresponding to the user interaction.

6. The method of claim 1, wherein generating the pattern further comprises: Determining clothing attributes associated with the virtual clothing, the clothing attributes including at least any one of the following: clothing style, clothing color, clothing material, clothing type; as well as The pattern is generated using the generative model based on the clothing attributes.

7. The method of claim 1, wherein generating the pattern further comprises: Providing an interactive interface for specifying a processing technique for adding the pattern to the virtual garment, the processing technique comprising at least one of the following: a screen printing technique, a spraying technique, a transfer technique, and an embroidery technique; as well as In response to receiving a user interaction with the interactive interface, the pattern is generated using the generation model based on a processing technique corresponding to the user interaction.

8. The method of claim 1, wherein the pattern comprises a plurality of candidate patterns, and generating the customized garment image further comprises: In response to receiving a selection of a target pattern from among the plurality of candidate patterns, the customized garment image is generated based on the target pattern and the garment image.

9. The method of claim 1, wherein generating the customized garment image further comprises: Providing an interactive interface for specifying placement parameters of the pattern in the virtual garment, the placement parameters including at least any one of the following: position, size, direction; as well as In response to receiving a user interaction with the interactive interface, the pattern is added based on a placement parameter corresponding to the user interaction.

10. The method according to claim 1, further comprising: receiving a user image for specifying a character to try on the customized virtual clothing; as well as Based on the user image and the customized clothing image, a fitting effect image of the customized virtual clothing is generated.

11. The method according to claim 10, wherein generating the try-on effect image comprises: Recognizing a facial image in the user image; as well as In response to determining that the facial image satisfies a first predetermined condition, a fusion model is called to replace the model face in the model image with the facial image to generate the fitting effect image, wherein the model image includes a fitting effect of the model trying on the customized virtual clothing.

12. The method according to claim 10, wherein generating the try-on effect image comprises: identifying a torso image in the user image; as well as In response to determining that the torso image satisfies a second predetermined condition, a fusion model is called to replace the clothing part in the torso image with the customized clothing image to generate the fitting effect image.

13. The method according to claim 1, wherein the method is called in a social network application, and the method further comprises: Providing an interactive interface for publishing the customized virtual clothing; as well as In response to receiving a user interaction with the interactive interface, the customized virtual garment is published in the social networking application.

14. The method according to claim 13, wherein publishing the customized virtual clothing in the social networking application comprises at least any one of the following: publishing the customized virtual garment in a user account of the user interaction in the social networking application; and The customized virtual clothing is published in an activity space in the social networking application for providing customization of the virtual clothing.

15. A device for customizing virtual clothing, comprising: an acquisition module configured to acquire a customization request, the customization request specifying a pattern to be added to a virtual garment to be customized; a pattern generation module configured to generate the pattern to be added to the virtual garment based on the customization request by using a generation model; as well as The image generation module is configured to generate a customized garment image of the customized virtual garment based on the pattern and the garment image of the virtual garment.

16. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 14 when executed by the at least one processing unit.

17. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the processor to implement the method according to any one of claims 1 to 14.

Images