Virtual image creating method and device and electronic equipment

Abstract

The embodiment of the invention provides a virtual image creating method and device and electronic equipment, and relates to the technical field of three-dimensional modeling, the method is applied to the electronic equipment, and the method comprises the following steps: acquiring a plurality of face images of a to-be-virtualized object collected from multiple angles; constructing a head model of the to-be-virtualized object and a mapping file of the head model based on the plurality of face images by using a first model making tool; converting the head model and the mapping file into an editable file in a specified format by utilizing a model editing plug-in arranged in a second model making tool, and obtaining a target file of a virtual image of the object to be virtualized obtained by editing the editable file; and creating a virtual image of the to-be-virtualized object based on the target file by using a second model making tool. Compared with the prior art, by applying the scheme provided by the embodiment of the invention, the creation efficiency of the virtual image can be improved on the basis of truly restoring the real image of the to-be-virtualized object.

Description

Technical Field

[0001] The present application relates to the technical field of three-dimensional modeling, and in particular to a method, device and electronic device for creating a virtual image. Background Art

[0002] As 3D (three-dimensional) modeling technology becomes more mature, using 3D modeling technology to create virtual images and realize the interaction between virtual images and people has become a trend in the current social application of 3D modeling technology. For example, virtual images that can interact with users in game scenes and virtual images that interpret storylines in animation scenes.

[0003] In the related art, in order to more realistically restore the real image of the virtual object, usually, professionals need to use three-dimensional modeling software to carve according to the real image of the virtual object to make a model of the virtual object, and bake the texture of the virtual object through texture making software, so as to obtain the model of the virtual object. Then, professionals will build the skeleton and skin the above model, and then complete the final virtual image of the virtual object. However, the above process of making the virtual image of the virtual object is too complicated and cumbersome, resulting in low efficiency in creating the virtual image.

[0004] Based on this, how to improve the efficiency of creating virtual images on the basis of truly restoring the real image of the virtual object has become a problem that needs to be solved urgently. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method, device and electronic device for creating a virtual image, so as to improve the efficiency of creating a virtual image on the basis of truly restoring the real image of the virtual object. The specific technical solution is as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for creating a virtual image, which is applied to an electronic device, and the method includes:

[0007] Acquire multiple facial images of the object to be virtualized collected from multiple angles;

[0008] Using a first model making tool, based on the multiple facial images, construct a head model of the object to be virtualized and a texture file of the head model;

[0009] Using a model editing plug-in provided in the second model making tool, the head model and the texture file are converted into editable files of a specified format, and a target file of the virtual image of the object to be virtualized is obtained by editing the editable file;

[0010] The second model making tool is used to create a virtual image of the object to be virtualized based on the target file.

[0011] Optionally, in a specific implementation, before using the first model making tool to construct the head model of the object to be virtualized and the texture file of the head model based on the multiple facial images, the method further includes:

[0012] Performing preset image processing on the multiple facial images respectively to obtain multiple target images; wherein the preset image processing includes: highlight removal processing and / or shadow removal processing;

[0013] The step of using the first model making tool to construct the head model of the object to be virtualized and the texture file of the head model based on the multiple facial images includes:

[0014] A first model making tool is used to construct a head model of the object to be virtualized and a texture file of the head model based on the multiple target images.

[0015] Optionally, in a specific implementation, the using the first model making tool to construct the head model of the to-be-virtualized object and the texture file of the head model based on the multiple facial images includes:

[0016] When a first import instruction about the plurality of facial images is detected, the plurality of facial images are imported into a first model making tool, so that the first model making tool aligns the plurality of facial images according to the angle relationship between the facial images, and uses the aligned plurality of facial images to construct a head model of the object to be virtualized and a texture file of the head model;

[0017] When a first export instruction regarding the head model and the texture file is detected, the head model and the texture file are exported from the first model making tool.

[0018] Optionally, in a specific implementation, the converting the head model and the texture file into editable files of a specified format by using a model editing plug-in provided in the second model making tool, and acquiring a target file of the virtual image of the object to be virtualized obtained by editing the editable file, comprises:

[0019] When a second import instruction regarding the head model and the texture file is detected, the head model and the texture file are imported into a second model making tool, so that a model editing plug-in provided in the second model making tool converts the head model and the texture file into editable files in a specified format, and uploads the editable files to a virtual image creation website corresponding to the model editing plug-in, so that the virtual image creation website generates a target file of the virtual image of the object to be virtualized based on the editing operation on the editable files;

[0020] When a download instruction for the target file is detected, the target file is downloaded from the avatar creation website to the second model making tool using a download plug-in provided in the second model making tool.

[0021] Optionally, in a specific implementation, the method further includes:

[0022] Downloading the target file from the avatar creation website using a download tool;

[0023] Modifying the target file downloaded by using the download tool to obtain a modified file;

[0024] When a third import instruction regarding the modified file is detected, the target file in the second model making tool is replaced with the modified file.

[0025] Optionally, in a specific implementation, the method further includes:

[0026] Acquiring motion information of the virtual object in motion captured by a motion capture device;

[0027] The second model making tool is used to control the virtual image to perform an action matching the action information based on the action information.

[0028] In a second aspect, an embodiment of the present application provides a virtual image creation device, which is applied to an electronic device, and the device includes:

[0029] A facial image acquisition module, used to acquire multiple facial images of the virtual object collected from multiple angles;

[0030] A construction module, configured to construct a head model of the object to be virtualized and a texture file of the head model based on the multiple facial images using a first model making tool;

[0031] a target file acquisition module, used to convert the head model and the texture file into editable files of a specified format by using a model editing plug-in provided in the second model making tool, and to acquire a target file of the virtual image of the object to be virtualized obtained by editing the editable file;

[0032] The virtual image creation module is used to use the second model making tool to create a virtual image of the object to be virtualized based on the target file.

[0033] Optionally, in a specific implementation, the device further includes:

[0034] An image processing module is used to perform preset image processing on the multiple facial images respectively to obtain multiple target images before constructing the head model of the virtual object and the texture file of the head model based on the multiple facial images using the first model making tool; wherein the preset image processing includes: highlight removal processing and / or shadow removal processing;

[0035] The building blocks are specifically used for:

[0036] A first model making tool is used to construct a head model of the object to be virtualized and a texture file of the head model based on the multiple target images.

[0037] Optionally, in a specific implementation, the building module is specifically used to:

[0038] When a first import instruction about the plurality of facial images is detected, the plurality of facial images are imported into a first model making tool, so that the first model making tool aligns the plurality of facial images according to the angle relationship between the facial images, and uses the aligned plurality of facial images to construct a head model of the object to be virtualized and a texture file of the head model;

[0039] When a first export instruction regarding the head model and the texture file is detected, the head model and the texture file are exported from the first model making tool.

[0040] Optionally, in a specific implementation, the target file acquisition module is specifically used to:

[0041] When a second import instruction regarding the head model and the texture file is detected, the head model and the texture file are imported into a second model making tool, so that a model editing plug-in provided in the second model making tool converts the head model and the texture file into editable files in a specified format, and uploads the editable files to a virtual image creation website corresponding to the model editing plug-in, so that the virtual image creation website generates a target file of the virtual image of the object to be virtualized based on the editing operation on the editable files;

[0042] When a download instruction for the target file is detected, the target file is downloaded from the avatar creation website to the second model making tool using a download plug-in provided in the second model making tool.

[0043] Optionally, in a specific implementation, the device further includes:

[0044] The file replacement module is used to download the target file from the virtual image creation website using a download tool; modify the target file downloaded using the download tool to obtain a modified file; and when a third import instruction regarding the modified file is detected, replace the target file in the second model making tool with the modified file.

[0045] Optionally, in a specific implementation, the device further includes:

[0046] A motion capture module, used to obtain motion information of the virtual object in motion captured by a motion capture device;

[0047] An action control module is used to use the second model making tool to control the virtual image to perform an action matching the action information based on the action information.

[0048] In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0049] Memory, used to store computer programs;

[0050] The processor is used to implement the method steps of any virtual image creation method provided in the first aspect when executing the program stored in the memory.

[0051] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps of any virtual image creation method provided in the first aspect above are implemented.

[0052] In a fifth aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method steps of any one of the virtual image creation methods provided in the first aspect above.

[0053] Beneficial effects of the embodiments of the present application:

[0054] As can be seen from the above, by applying the solution provided in the embodiment of the present application, when creating a virtual image, multiple facial images of the object to be virtualized collected from multiple angles can be obtained. Therefore, after obtaining the multiple facial images, the first model making tool is used to construct the head model to be virtualized and the texture file of the head model based on the multiple facial images. Then, the model editing plug-in set in the second model making tool can be used to convert the head model and the texture file into editable files of a specified format. Thus, the target file of the virtual image to be virtualized obtained by editing the editable file can be obtained. In this way, the second model making tool can be used to create the virtual image of the object to be virtualized based on the target file.

[0055] Based on this, by using the solution provided by the embodiment of the present application, the head model of the object to be virtualized is produced by using the acquired facial images of the object to be virtualized at multiple angles, which can shorten the production cycle of the head model, and the virtual image of the object to be virtualized is constructed and edited by using multiple model production tools, thereby improving the efficiency of creating the virtual image. In addition, by using the above-mentioned facial images to produce the head model of the object to be virtualized and the texture file of the head model, the facial features and skin condition of the object to be virtualized can be truly restored, thereby making the produced virtual image more close to the real image of the object to be virtualized. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0057] Figure 1 A schematic diagram of the process of a first virtual image creation method provided in an embodiment of the present application;

[0058] Figure 2 A schematic diagram of a second method for creating a virtual image provided in an embodiment of the present application;

[0059] Figure 3 A schematic diagram of a process of creating a third virtual image provided in an embodiment of the present application;

[0060] Figure 4 A schematic diagram of a fourth method for creating a virtual image provided in an embodiment of the present application;

[0061] Figure 5 A schematic diagram of a fifth method for creating a virtual image provided in an embodiment of the present application;

[0062] Figure 6 A schematic diagram of a sixth method for creating a virtual image provided in an embodiment of the present application;

[0063] Figure 7 A schematic diagram of a specific embodiment provided for the present application;

[0064] Figure 8 A schematic diagram of a specific embodiment provided for the present application;

[0065] Fig. 9 A schematic diagram of the structure of a virtual image creation device provided in an embodiment of the present application;

[0066] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field based on this application belong to the scope of protection of the present invention.

[0068] In the related art, in order to more realistically restore the real image of the virtual object, usually, professionals need to use three-dimensional modeling software to carve according to the real image of the virtual object to make a model of the virtual object, and use texture making software to bake the texture of the virtual object, thereby obtaining the model of the virtual object. Then, professionals will build the skeleton and skin the above model, and then complete the final virtual image of the virtual object. However, the above process of making the virtual image of the virtual object is too complicated and cumbersome, resulting in low efficiency in creating the virtual image. Based on this, how to improve the efficiency of creating the virtual image on the basis of realistically restoring the real image of the virtual object has become a problem that needs to be solved urgently.

[0069] In order to solve the above technical problems, an embodiment of the present application provides a method for producing a virtual image.

[0070] Among them, the method can be applied to various application scenarios that require the production of virtual images, for example, the production of virtual images of actors in 3D movies, the production of virtual images of game characters in 3D games, the production of virtual images of animation characters in 3D animations, etc. In addition, the method can be applied to various electronic devices such as tablet computers, laptop computers, desktop computers, etc., hereinafter referred to as electronic devices. Among them, the electronic device can be an independent electronic device, for example, an independent desktop computer; or it can be multiple electronic devices, for example, a device cluster composed of multiple desktop computers. Based on this, the embodiments of the present application do not limit the application scenarios and execution subjects of the method.

[0071] In the technical solution of this application, the operations involved in obtaining, storing, using, processing, transmitting, providing and disclosing user personal information are all carried out with the user's authorization.

[0072] A method for creating a virtual image provided in an embodiment of the present application, applied to an electronic device, may include the following steps:

[0073] Acquire multiple facial images of the object to be virtualized collected from multiple angles;

[0074] Using a first model making tool, based on a plurality of facial images, construct a head model of the object to be virtualized and a texture file of the head model;

[0075] Using a model editing plug-in provided in the second model making tool, the head model and the texture file are converted into an editable file in a specified format, and a target file of the virtual image of the object to be virtualized is obtained by editing the editable file;

[0076] Using the second model making tool, a virtual image of the object to be virtualized is created based on the target file.

[0077] As can be seen from the above, by applying the solution provided in the embodiment of the present application, when creating a virtual image, multiple facial images of the object to be virtualized collected from multiple angles can be obtained. Therefore, after obtaining the multiple facial images, the first model making tool is used to construct the head model to be virtualized and the texture file of the head model based on the multiple facial images. Then, the model editing plug-in set in the second model making tool can be used to convert the head model and the texture file into editable files of a specified format. Thus, the target file of the virtual image to be virtualized obtained by editing the editable file can be obtained. In this way, the second model making tool can be used to create the virtual image of the object to be virtualized based on the target file.

[0078] Based on this, by using the solution provided by the embodiment of the present application, the head model of the object to be virtualized is produced by using the acquired facial images of the object to be virtualized at multiple angles, which can shorten the production cycle of the head model, and the virtual image of the object to be virtualized is constructed and edited by using multiple model production tools, thereby improving the efficiency of creating the virtual image. In addition, by using the above-mentioned facial images to produce the head model of the object to be virtualized and the texture file of the head model, the facial features and skin condition of the object to be virtualized can be truly restored, thereby making the produced virtual image more close to the real image of the object to be virtualized.

[0079] A method for creating a virtual image provided in an embodiment of the present application is described in detail below in conjunction with the accompanying drawings.

[0080] Figure 1 A flowchart of a method for creating a virtual image provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method may include the following steps S101-S104.

[0081] S101: Acquire multiple facial images of the object to be virtualized collected from multiple angles.

[0082] Specifically, the process of creating a virtual image is to use the real image of the object to be virtualized to construct the virtual image of the object to be virtualized. Therefore, when making the virtual image of the object to be virtualized, the image of the real image of the object to be virtualized can be obtained first.

[0083] In this way, before making a virtual image of the object to be virtualized, the electronic device can obtain multiple facial images of the object to be virtualized collected from multiple angles, so that the facial features and skin condition of the object to be virtualized can be determined from the multiple facial images obtained, so as to facilitate the subsequent use of the facial images of the object to be virtualized to make a head model of the object to be virtualized.

[0084] Optionally, an image acquisition device is used to acquire facial images of the object to be virtualized from multiple angles, and for each angle, the facial image of the object to be virtualized acquired by the image acquisition device at that angle is sent to an electronic device.

[0085] When collecting multiple facial images of the object to be virtualized, the images may be collected at preset angles, or multiple facial images at multiple angles may be collected around the object to be virtualized. This embodiment of the present application does not make any specific limitation on this.

[0086] Optionally, facial images of the object to be virtualized at multiple angles are captured from the image data of the object to be virtualized.

[0087] For example, in a video about a to-be-virtualized object, a facial image of the front, a facial image of the left, a facial image of the right, and a facial image of the back of the to-be-virtualized object are captured.

[0088] In this way, the acquired facial images of the object to be virtualized at multiple angles can be used to construct a head model of the object to be virtualized and a texture file of the head model.

[0089] S102: Using a first model making tool, based on a plurality of facial images, construct a head model of the object to be virtualized and a texture file of the head model.

[0090] After the electronic device acquires multiple facial images of the object to be virtualized, it can use the first model making tool to align the facial images based on the facial images acquired at various angles according to the angle relationship corresponding to the facial images, and knead the aligned facial images into a head model of the object to be virtualized. Then, the skin condition, facial features and other information of the object to be virtualized in the multiple facial images are determined as a texture file of the head model.

[0091] For example, the multiple facial images of the object to be virtualized acquired from multiple angles include: front image 1 of the object to be virtualized, left image 2 of the object to be virtualized, back image 3 of the object to be virtualized, and right image 4 of the object to be virtualized. After acquiring the above four images, the electronic device can use the first model making tool to align the above four images according to the corresponding angles, and knead the aligned images into a head model of the object to be virtualized. Then, the skin condition, facial features and other information of the object to be virtualized in the above four images are determined as the texture file of the head model.

[0092] The first model making tool is a 3D model making tool that uses multiple facial images of the same object to generate a head model of the object and a texture file of the head model, and the generated head model is a 3D head model. That is, the first model making tool can be a 3D model making tool for making a 3D head model.

[0093] For example, the first model making tool may be RealityCapture (a rapid modeling software based on images and 3D point clouds), wherein RealityCapture can automatically extract exquisite and accurate 3D models from a set of ordinary images or laser scanning images, and can extract high-quality model texture resources (i.e., texture files) from the above-mentioned image resources to generate the above-mentioned 3D models.

[0094] Based on this, optionally, in a specific implementation, such as Figure 2As shown, it is a flowchart of a method for creating a virtual image provided in an embodiment of the present application. In the method for creating a virtual image provided in an embodiment of the present application, the above step S102 may include the following steps S1021-S1022:

[0095] S1021: when a first import instruction regarding a plurality of facial images is detected, the plurality of facial images are imported into a first model making tool, so that the first model making tool aligns the plurality of facial images according to an angle relationship between the facial images, and uses the aligned plurality of facial images to construct a head model of the object to be virtualized and a texture file of the head model;

[0096] S1022: When a first export instruction regarding the head model and the texture file is detected, export the head model and the texture file from the first model making tool.

[0097] In this specific implementation, when the electronic device detects a first import instruction regarding a plurality of facial images, the electronic device imports the plurality of facial images into a first model making tool.

[0098] After receiving the above-mentioned multiple facial images, the first model making tool can align the above-mentioned multiple facial images according to the angle relationship between each facial image, so as to construct the head model of the virtual object and the texture file of the head model using the aligned multiple facial images.

[0099] When the electronic device detects the first export instruction regarding the texture file of the head model, it can export the constructed head model and texture file from the first model making tool.

[0100] In this way, by directly constructing a head model of the virtual object using multiple facial images of the virtual object, a lot of model making time can be saved, and the production cycle of the virtual image of the virtual object can be shortened, thereby improving the production efficiency of the virtual image. In addition, in the process of constructing the head model of the virtual object using multiple facial images, the art expertise involved is relatively shallow, and the art expertise required of the user is relatively low, thereby reducing the consumption of labor costs.

[0101] S103: using a model editing plug-in provided in the second model making tool, converting the head model and the texture file into an editable file of a specified format, and acquiring a target file of the virtual image of the object to be virtualized obtained by editing the editable file.

[0102] The head model of the object to be virtualized and the texture file of the head model obtained by the electronic device using the first model making tool have a lower restoration degree than the real image of the object to be virtualized. In order to more accurately restore the real image of the image to be virtualized, after obtaining the head model of the object to be virtualized and the texture file of the head model, the electronic device can use the head model as a basic model and the texture file as a basic texture to perform secondary editing on the head model and the texture file.

[0103] However, the head model and texture file obtained by the first model making tool are usually not editable. Therefore, the head model and texture file can be converted into editable files in a specified format using a model editing plug-in provided in the second model making tool, so that the head model and texture file can be edited again by using the model editing plug-in corresponding to the avatar creation website.

[0104] Since different virtual image creation websites support different file formats, the format of the editable file that can be converted by the model editing plug-in set in the second model making tool of the electronic device determines the type of virtual image creation website used by the electronic device when editing the editable file.

[0105] The second model making tool is a 3D model creation tool for editing existing 3D models and model texture resources (i.e., texture files) of the 3D models. That is, the second model making tool can be a 3D creation tool for creating a 3D virtual image.

[0106] For example, the second model making tool may be UE5 (Unreal Engine 5), wherein UE5 may perform real-time three-dimensional creation.

[0107] Optionally, the model editing plug-in provided in the second model making tool may be a creation plug-in for creating a virtual image, such as a MetaHuman plug-in, etc. The MetaHuman plug-in is a plug-in for editing a digital human. Thus, a lot of time for skeleton construction and skinning can be saved, and the efficiency of creating a virtual image can be improved.

[0108] In this way, after the electronic device uses the model editing plug-in set in the second model making tool to convert the above-mentioned head model and texture file into an editable file of a specified format, the above-mentioned editable file can be uploaded to the virtual image creation website corresponding to the model editing plug-in. Thus, in the virtual image creation website, the above-mentioned editable file can be edited based on the editing operation on the editable file to obtain the target file of the virtual image of the above-mentioned virtual object.

[0109] The above-mentioned editing operations on the editable file may include: editing operations on the hair of the virtual object, editing operations on the facial features of the virtual object, editing operations on the clothing of the virtual object, and editing operations on the texture of the virtual object, etc. This embodiment of the application does not make specific limitations on this.

[0110] For example, the avatar creation website corresponding to the model editing plug-in A set in the second model making tool of the electronic device is the avatar creation website A', and the file format supported by the avatar creation website A' is the specified format a.

[0111] Therefore, the electronic device can use the model editing plug-in A set in the second model making tool to convert the head model of the virtual object and the texture file of the head model into an editable file a1 under the specified format a, so that the editable file a1 can be edited in the virtual image creation website A', thereby obtaining the target file of the virtual image of the above-mentioned virtual object.

[0112] Based on this, optionally, in a specific implementation, such as Figure 3 As shown, it is a flowchart of a method for creating a virtual image provided in an embodiment of the present application. In the method for creating a virtual image provided in an embodiment of the present application, the above step S103 may include the following steps S1031-S1032:

[0113] S1031: when a second import instruction regarding the head model and the texture file is detected, the head model and the texture file are imported into the second model making tool, so that the model editing plug-in set in the second model making tool converts the head model and the texture file into an editable file in a specified format, and uploads the editable file to a virtual image creation website corresponding to the model editing plug-in, so that the virtual image creation website generates a target file of the virtual image of the object to be virtualized based on the editing operation on the editable file;

[0114] S1032: When a download instruction for the target file is detected, the target file is downloaded from the avatar creation website to the second model making tool using a download plug-in provided in the second model making tool.

[0115] In this specific implementation, when the electronic device detects the second import instruction regarding the head model and the texture file of the virtual object, it can import the head model and the texture file into the second model making tool.

[0116] After receiving the head model and the texture file, the second model making tool can use the model editing plug-in set by itself to convert the head model and the texture file into an editable file of a specified format. Then, the editable file can be uploaded to the virtual image creation website corresponding to the model editing plug-in, so that the virtual image creation website generates the target file of the virtual image of the virtual object to be virtualized based on the editing operation on the editable file.

[0117] When the electronic device detects a download instruction for the target file, it can use the download plug-in provided in the second model making tool to download the target file from the virtual image creation website to the second model making tool.

[0118] In this way, by editing the head model of the virtual object and the texture file of the head model, the obtained virtual image is made to be more consistent with the real image of the virtual object, thereby improving the restoration degree of the virtual image.

[0119] Optionally, the download plug-in preset in the second model making tool may be a download plug-in for downloading the target file of the avatar, for example, a QuixelBridge module, wherein QuixelBridge is software for storing and downloading digital assets.

[0120] S104: Using the second model making tool, based on the target file, create a virtual image of the object to be virtualized.

[0121] After receiving the target file of the object to be virtualized, the second model making tool can create a virtual image of the object to be virtualized based on the target file.

[0122] As can be seen from the above, by applying the solution provided in the embodiment of the present application, when creating a virtual image, multiple facial images of the object to be virtualized collected from multiple angles can be obtained. Therefore, after obtaining the multiple facial images, the first model making tool is used to construct the head model to be virtualized and the texture file of the head model based on the multiple facial images. Then, the model editing plug-in set in the second model making tool can be used to convert the head model and the texture file into editable files of a specified format. Thus, the target file of the virtual image to be virtualized obtained by editing the editable file can be obtained. In this way, the second model making tool can be used to create the virtual image of the object to be virtualized based on the target file.

[0123] Based on this, by using the solution provided by the embodiment of the present application, the head model of the object to be virtualized is produced by using the acquired facial images of the object to be virtualized at multiple angles, which can shorten the production cycle of the head model, and the virtual image of the object to be virtualized is constructed and edited by using multiple model production tools, thereby improving the efficiency of creating the virtual image. In addition, by using the above-mentioned facial images to produce the head model of the object to be virtualized and the texture file of the head model, the facial features and skin condition of the object to be virtualized can be truly restored, thereby making the produced virtual image more close to the real image of the object to be virtualized.

[0124] Since the created virtual image will be used in different virtual scenes, different light sources will be set in different virtual scenes. When light shines on the face of the virtual image from different angles, different degrees of facial shadows and facial highlights will be formed. When shooting the facial image of the virtual object, the light source in the shooting scene will form different degrees of facial shadows and facial highlights on the face of the virtual object, resulting in facial shadows and facial highlights in the captured facial image.

[0125] If the acquired facial image carries different degrees of facial shadows and facial highlights, it may cause visual dissonance to the user for the virtual image in different virtual scenes, resulting in a low degree of restoration of the virtual image. Therefore, in order to improve the degree of restoration of the virtual image of the virtual object in different virtual scenes, after acquiring the facial image of the virtual object, the acquired facial image may be processed to remove the facial highlights and facial shadows that may affect the virtual object.

[0126] Based on this, optionally, in a specific implementation, such as Figure 4 FIG. 4 is a flow chart of a method for creating a virtual image provided by an embodiment of the present application. The method for creating a virtual image provided by an embodiment of the present application may further include the following step S401:

[0127] S401: performing preset image processing on a plurality of facial images respectively to obtain a plurality of target images;

[0128] The preset image processing includes: highlight removal processing and / or shadow removal processing.

[0129] In this specific implementation, before using the first model making tool to construct a head model of the object to be virtualized and a texture file of the head model based on multiple facial images, the multiple facial images of the object to be virtualized obtained can be subjected to de-highlighting processing and / or de-shadowing processing, respectively, so as to obtain multiple target images.

[0130] In this way, when the virtual image is subsequently simulated in different virtual scenes, the virtual image can be presented more naturally, thereby improving the restoration degree of the virtual image.

[0131] When performing the preset image processing on multiple facial images respectively, the preset image processing may be performed on each facial image in turn, or the preset image processing may be performed on all facial images. This embodiment of the present application does not make any specific limitation on this.

[0132] Optionally, a preset image processing tool may be used to perform preset image processing on multiple facial images. The preset image processing tool may include: Lightroom (Adobe Photoshop Lightroom, LR image processing software), so that batch editing and processing of images can be convenient.

[0133] Accordingly, the above step S102, using the first model making tool to construct a head model of the object to be virtualized and a texture file of the head model based on multiple facial images, may include the following step S402:

[0134] S402: Using a first model making tool, based on a plurality of target images, construct a head model of the object to be virtualized and a texture file of the head model.

[0135] In this specific implementation, after acquiring multiple target images of the object to be virtualized, the electronic device can use the first model making tool to align the target images based on the acquired target images at various angles according to the angle relationship corresponding to each target image, and knead the aligned target images into a head model of the object to be virtualized. Then, the skin condition, facial features and other information of the object to be virtualized in the multiple target images are used as a texture file of the head model.

[0136] For example, the multiple target images of the object to be virtualized acquired from multiple angles include: a front image 1 of the object to be virtualized that has been de-highlighted and / or de-shadowed, a left image 2 of the object to be virtualized that has been de-highlighted and / or de-shadowed, a back image 3 of the object to be virtualized that has been de-highlighted and / or de-shadowed, and a right image 4 of the object to be virtualized that has been de-highlighted and / or de-shadowed. After the electronic device acquires the above four target images, it can use the first model making tool to align the above four target images according to the corresponding angles, and knead the aligned target images into a head model of the object to be virtualized. Then, the skin condition, facial features and other information of the object to be virtualized in the above four target images are used as the texture file of the above head model.

[0137] In some cases, the created virtual image may need to be modified and adjusted so that the presentation effect of the virtual image reaches the effect expected by the user.

[0138] Based on this, optionally, in a specific implementation, such as Figure 5 FIG. 5 is a flow chart of a method for creating a virtual image provided by an embodiment of the present application. The method for creating a virtual image provided by an embodiment of the present application may further include the following steps S501-S503:

[0139] S501: Downloading a target file from a virtual image creation website using a download tool;

[0140] S502: modifying the target file downloaded by using the download tool to obtain a modified file;

[0141] S503: When a third import instruction about a modified file is detected, the target file in the second model making tool is replaced with the modified file.

[0142] In this specific implementation, if the presentation effect of the virtual image does not meet the user's expectations, the electronic device can use a download tool to download the target file of the virtual image of the object to be virtualized from the virtual image creation website.

[0143] The download tool is a tool for downloading files from the virtual image creation website corresponding to the model editing plug-in in the second model making tool. That is, the download tool can be a download tool for downloading target files of the virtual image.

[0144] For example, the download tool may be a QuixelBridge download tool, wherein the QuixelBridge download tool may download the target file of the virtual image of the object to be virtualized from the virtual image creation website corresponding to the model editing plug-in in the second model making tool. In the case where the download tool is the QuixelBridge download tool, the virtual image creation website may be MetaHumanCreator.

[0145] Furthermore, the target file is a file of the virtual image of the object to be virtualized edited by the model editing plug-in in the second model making tool, which may record the relevant data of the head model of the virtual image of the object to be virtualized, for example, recording the model parameters of the head model such as hairstyle and skin color. That is, the target file may include a file for storing the head model of the virtual image of the object to be virtualized.

[0146] For example, the above target file may be a Maya (Autodesk Maya, Maya) source file, wherein Maya is software used for 3D modeling rendering and 3D animation production.

[0147] In this way, after downloading the above-mentioned target file, the electronic device can modify the above-mentioned target file according to the user's needs to obtain a modified file. Thus, when the third import instruction regarding the modified file is detected, the target file in the second model making tool can be replaced with the modified file, and then, the above-mentioned second model making tool can be used to update the virtual image of the virtual object based on the above-mentioned modified file.

[0148] Among them, when modifying the above-mentioned target file, the head model and the texture file of the head model included in the above-mentioned target file can be modified to obtain the modified head model and the modified texture file. Specifically, the modified head model can be matched to the three-dimensional head model constructed by the above-mentioned first model making tool, and then, by using the method of baking textures, the texture file constructed by the above-mentioned first model making tool is baked into the above-mentioned modified head model, thereby producing a texture file matching the modified head model, and adding the modified head model to the virtual image created by the head model before through the fusion deformation tool, and then, importing the above-mentioned added head model and texture file into the above-mentioned second model making tool, replacing the head model and the texture file of the virtual image constructed by the first model making tool before, and completing the modification of the virtual image of the virtual object.

[0149] The above-mentioned blending deformation tool may be a BlendShape tool.

[0150] Optionally, when the first model making tool is RealityCapture, the obtained model may include a head high model of the virtual image of the virtual object to be virtualized, wherein the so-called head high model refers to a three-dimensional head model with a high number of faces.

[0151] Optionally, the target file downloaded from the virtual image creation website corresponding to the model editing plug-in in the second model making tool using the above-mentioned download tool can store a simple head model of the virtual image of the object to be virtualized. For example, the above-mentioned Maya source file can store a simple head model of the virtual image of the object to be virtualized. The so-called simple head model refers to a three-dimensional head model with a relatively low number of faces, which is generally a low-polygon head model based on a topology of a high-polygon head model, and the details are relatively rough compared with the high-polygon head model.

[0152] Specifically, in order to make the behavioral characteristics of the virtual image more closely match the behavioral characteristics of the object to be virtualized, a motion capture device can be used to capture the motion information of the object to be virtualized during movement, thereby imparting the above motion information to the virtual image, making the virtual image more closely match the object to be virtualized from its appearance to its movement and reducing the visual dissonance caused by the mismatch between the behavioral characteristics of the virtual image and the object to be virtualized during movement.

[0153] Based on this, optionally, in a specific implementation, such as Figure 6 FIG. 1 is a flow chart of a method for creating a virtual image provided by an embodiment of the present application. The method for creating a virtual image provided by an embodiment of the present application may further include the following steps S105-S106:

[0154] S105: Acquiring motion information of the virtual object captured by the motion capture device during the motion process;

[0155] S106: Using the second model making tool, based on the action information, control the virtual image to perform an action matching the action information.

[0156] In this specific implementation, a motion capture device can be used to capture the motion information of the virtual object during movement. Thus, after obtaining the above motion information, the electronic device can use a second model making tool to control the created virtual image to perform actions matching the above motion information.

[0157] In order to facilitate understanding of the above-mentioned method for creating a virtual image provided by the embodiment of the present application, Figure 7 The figure is a flow chart of a specific embodiment provided by the present application.

[0158] The specific embodiment may include the following steps S701-S715:

[0159] S701: Take a photo.

[0160] In this specific embodiment, when creating a virtual image of the object to be virtualized, the electronic device can use the image acquisition device carried by the electronic device to capture multiple facial images of the object to be virtualized.

[0161] S702: Processing photos.

[0162] After obtaining the multiple facial images of the objects to be virtualized, the electronic device may perform preset image processing, such as denoising, on the multiple facial images respectively to obtain multiple target images.

[0163] S703: Generate models and textures using RealityCapture.

[0164] After obtaining the above-mentioned multiple target images, the electronic device can import the above-mentioned multiple target images into the first model making tool, and call the first model making tool, so that the first model making tool uses the multiple target images to construct the head model of the virtual object and the texture file of the head model. Then, the electronic device can export the above-mentioned head model and texture file from the first model making tool.

[0165] For example, the first model making tool may be RealityCapture.

[0166] S704: Enter UE5 to generate MetaHuman resources.

[0167] After obtaining the above-mentioned head model and texture file, the electronic device can import the above-mentioned head model and texture file into the second model making tool, so that the model editing plug-in set in the second model making tool can convert the silly head model and texture file into an editable file in a specified format.

[0168] For example, the second model making tool may be UE5, and the model editing plug-in set in the second model making tool may be a MetaHuman plug-in. Furthermore, in this case, the editable file obtained by converting the head model and texture file by the model editing plug-in set in the second model making tool may be called a MetaHuman resource.

[0169] S705: Edit the MetaHumanCreater website to generate hair, textures, clothing, etc.; if the presentation effect of the obtained virtual image meets the user's expectations, execute step S706: if the presentation effect of the obtained virtual image does not meet the user's expectations, execute step S709.

[0170] After obtaining the above-mentioned editable file, the electronic device can upload the above-mentioned editable file to the virtual image creation website corresponding to the model editing plug-in set in the second model making tool, so that the virtual image creation website can generate a target file of the virtual image of the object to be virtualized based on the editing operation on the editable file. That is, the virtual image creation website can receive the user's editing operation on the editable file, thereby, based on the above-mentioned editing operation, generating the image content such as hair, texture, clothing, etc. of the virtual image of the object to be virtualized indicated by the above-mentioned editing operation, and recording the image content of the virtual image of the object to be virtualized generated in the target file. Obviously, the user can edit the virtual image of the object to be virtualized that he or she desires through the virtual image creation website.

[0171] For example, the second model making tool may be UE5, and the model editing plug-in provided in the second model making tool may be a MetaHuman plug-in. Accordingly, the virtual image creation website corresponding to the model editing plug-in provided in the second model making tool may be a MetaHumanCreater website.

[0172] S706: Download MetaHumanCreator resources through the built-in Bridge of UE5.

[0173] S707: Enter the motion capture phase to perform real-time capture.

[0174] S708: Make a short film through Sequence;

[0175] If the presentation effect of the virtual image of the virtual object to be virtualized generated in the above S705 reaches the effect expected by the user, the electronic device can use the download tool set in the second model making tool to download the above target file from the virtual image creation website corresponding to the model editing plug-in set in the above second model making tool. After the electronic device downloads the above target file, it can obtain the virtual image of the virtual object to be virtualized by parsing the above target file, so that the electronic device can enter the motion capture link (i.e., the action capture link) to perform motion capture on the virtual image of the virtual object to be virtualized, and through the short film production module set in the second model making tool, based on the actions captured in the above motion capture link, produce a short film of the virtual object to be virtualized.

[0176] For example, taking the second model making tool as UE5, the target file may be called MetaHumanCreator resource, the download tool may be the Bridge download tool, and the short film making module may be the Sequence tool.

[0177] S709: Download the character Maya source file through the independent Bridge;

[0178] If the presentation effect of the virtual image of the virtual object generated in S705 does not meet the user's expectations, the created virtual image needs to be modified and adjusted. Specifically: the electronic device can use an independent download tool to download the target file from the virtual image creation website corresponding to the model editing plug-in in the second model making tool.

[0179] For example, taking the second model making tool as UE5 as an example, the independent download tool may be an independent Bridge tool, and the target file may be a character Maya source file.

[0180] S710: Optimize the high-poly model exported from RealityCapture through ZBrush.

[0181] When modifying and adjusting the created virtual image, the electronic device may first use the 3D design software to optimize the head model of the virtual object constructed by the first model making tool. That is, the electronic device first derives the head model of the virtual object from the first model making tool, and then uses the head model obtained by optimizing the 3D design software.

[0182] For example, taking RealityCapture as the first model making tool, the 3D design software may be ZB (ie, digital sculpting and painting software, ZBrush), and the head model of the object to be virtualized constructed by the first model making tool is a high-poly model of the head.

[0183] S711: Export the simple head model from Maya.

[0184] After downloading the target file, the electronic device can derive the editable head model of the virtual object recorded in the target file from the target file.

[0185] For example, taking the second model making tool as UE5, the target file may be a Maya source file of a character, and the editable head model of the virtual object to be exported from the target file is a simple head model.

[0186] S712: Match the simple model to the high model optimized by ZB.

[0187] S713: Bake the scanned textures into a simple model and optimize the textures.

[0188] S714: The optimized head model is added to the original head model via BlendShape.

[0189] S715: Export the head model to UE5, replace the original model, and return to the above step S707.

[0190] After optimizing the head model constructed by the first model making tool and the head model derived from the target file, the head model included in the target file can be modified to obtain a modified head model and a modified texture file. Specifically, the head model derived from the target file is matched to the optimized head model constructed by the first model making tool to obtain a modified head model, and then, by baking scanning, the texture file constructed by the first model making tool is baked into the modified head model, thereby producing a texture file matching the modified head model, and optimizing the texture file of the produced modified head model. In this way, the modified head model can be added to the virtual image created by the head model by using the blending deformation tool, and then, the added head model and texture file are imported into the second model making tool to replace the head model and the texture file of the virtual image constructed by the first model making tool, thereby completing the modification of the virtual image of the virtual object.

[0191] For example, taking the second model making tool as UE5 as an example, the blending deformation tool may be a BlendShape tool.

[0192] In order to facilitate understanding of the above-mentioned method for creating a virtual image provided by the embodiment of the present application, Figure 8 The figure shows a schematic diagram of a specific embodiment provided by the present application.

[0193] The planning for this specific embodiment may include the following nine aspects:

[0194] Step 1: Scanning and modeling.

[0195] When creating a virtual image of the virtual object, the electronic device can use the image acquisition device carried by itself to acquire facial images of the virtual object from multiple angles, thereby creating the virtual image of the virtual object using the acquired multiple facial images. Specifically, the process includes sub-steps 1.1-1.3:

[0196] Sub-step 1.1, taking photos;

[0197] Sub-step 1.2, processing photos;

[0198] Sub-step 1.3, RealityCapture generates models and maps.

[0199] The electronic device uses the image acquisition device carried by itself to collect facial images of the object to be virtualized from multiple angles, and performs preset image processing such as denoising on the multiple facial images. Then, the electronic device can import the processed multiple facial images into the first model making tool, and call the first model making tool so that the first model making tool uses the processed multiple facial images to construct the head model of the object to be virtualized and the texture file of the head model. Then, the electronic device can export the head model and the texture file from the first model making tool. After obtaining the head model of the object to be virtualized and the texture file of the head model, it can enter step 2.

[0200] For example, the first model making tool may be RealityCapture. That is, after obtaining the head model of the virtual object and the texture file of the head model by using RealityCapture, step 2 may be entered.

[0201] Step 2: Enter UE5 to generate MetaHuman resources.

[0202] After obtaining the head model and the texture file, the electronic device can import the head model and the texture file into the second model making tool, so that the model editing plug-in set in the second model making tool can convert the silly head model and the texture file into an editable file of a specified format. After obtaining the editable file, step 3 can be entered.

[0203] For example, the second model making tool may be UE5, and the model editing plug-in set in the second model making tool may be a MetaHuman plug-in. Furthermore, in this case, the editable file converted by the model editing plug-in set in the second model making tool from the head model and the texture file may be called a MetaHuman resource. That is, after the obtained model and the texture of the model are imported into UE5 to generate a MetaHuman resource, and the generated MetaHuman resource is uploaded to the MetaHumanCreator website, step 3 may be entered.

[0204] Step 3: Enter MetaHuman editor to generate hair, textures, and clothing.

[0205] After obtaining the above-mentioned editable file, the electronic device can upload the above-mentioned editable file to the virtual image creation website corresponding to the model editing plug-in set in the second model making tool, so that the virtual image creation website can generate a target file of the virtual image of the object to be virtualized based on the editing operation on the editable file. That is, the virtual image creation website can receive the user's editing operation on the editable file, thereby, based on the above-mentioned editing operation, generating the image content such as hair, texture, clothing, etc. of the virtual image of the object to be virtualized indicated by the above-mentioned editing operation, and recording the image content of the virtual image of the object to be virtualized generated in the target file. Obviously, the user can edit the virtual image of the object to be virtualized that he or she desires through the virtual image creation website. After obtaining the above-mentioned target file, you can enter step 4.

[0206] For example, the second model making tool may be UE5, and the model editing plug-in provided in the second model making tool may be a MetaHuman plug-in. Accordingly, the virtual image creation website corresponding to the model editing plug-in provided in the second model making tool may be a MetaHumanCreater website.

[0207] Step 4: Download MetaHuman resources.

[0208] After the target file of the virtual image of the object to be virtualized is generated, the virtual image of the object to be virtualized and the target file can be obtained.

[0209] For example, the second model making tool may be UE5, the virtual image creation website corresponding to the model editing plug-in set in the second model making tool may be the MetaHumanCreater website, and the target file may be the character Maya source file. After the virtual image of the object to be virtualized is generated in the MetaHumanCreator website, the virtual image and the character Maya source file in the MetaHuman resource for generating the virtual image may be downloaded. Specifically, the sub-steps 4.1 and / or 4.2 are included:

[0210] Sub-step 4.1: Download MetaHumanCreator resources through UE5 built-in Bridge.

[0211] If the presentation effect of the virtual image of the virtual object generated by the above step 3 reaches the effect expected by the user, then sub-step 4.1 can be entered, and the electronic device can use the download tool set in the second model making tool to download the above target file from the virtual image creation website corresponding to the model editing plug-in set in the above second model making tool.

[0212] For example, if the second model making tool is UE5, the target file can be called MetaHumanCreator resource, and the download tool can be Bridge download tool. That is, by downloading MetaHumanCreator resource through Bridge built into UE5, you can enter step 8;

[0213] Sub-step 4.2: Download the character Maya source file through an independent Bridge.

[0214] If the presentation effect of the virtual image generated by the above step 4 does not meet the user's expectations, the above step 4.2 can be entered. The electronic device can use an independent download tool to download the above target file from the virtual image creation website corresponding to the model editing plug-in in the above second model making tool, thereby entering steps 5 to 7.

[0215] For example, taking the second model making tool as UE5, the independent download tool may be an independent Bridge tool, and the target file may be a character Maya source file, that is, by downloading the character Maya source file through an independent Bridge, it is possible to enter step 5 to step 7 to adjust the virtual image.

[0216] Step 5: Optimize the head model and texture;

[0217] Through the above step 5, the head model of the avatar and the texture of the head model can be optimized, specifically, including sub-steps 5.1-5.4:

[0218] Sub-step 5.1: Optimize the high-poly model exported from RealityCapture through ZBrush;

[0219] When modifying and adjusting the created virtual image, the electronic device may first use the 3D design software to optimize the head model of the virtual object constructed by the first model making tool. That is, the electronic device first derives the head model of the virtual object from the first model making tool, and then uses the head model obtained by optimizing the 3D design software.

[0220] For example, taking the first model making tool as RealityCapture, the 3D design software may be ZB (ie ZBrush), and the head model of the object to be virtualized constructed by the first model making tool is a high-poly model of the head.

[0221] Sub-step 5.2: Export the head model from Maya;

[0222] After downloading the target file, the electronic device can derive the editable head model of the virtual object recorded in the target file from the target file.

[0223] For example, taking the second model making tool as UE5, the target file may be a Maya source file of a character, and the editable head model of the virtual object to be exported from the target file is a simple head model.

[0224] Sub-step 5.3: Matching the simple model to the high model optimized by ZB

[0225] Sub-step 5.4: Bake the scanned textures into a simple model and optimize the textures.

[0226] After optimizing the head model constructed by the first model making tool and the head model derived from the target file, the head model included in the target file can be modified to obtain a modified head model and a modified texture file. Specifically, the head model derived from the target file is matched to the optimized head model constructed by the first model making tool to obtain a modified head model, and then, by baking scanning, the texture file constructed by the first model making tool is baked into the modified head model, thereby producing a texture file matching the modified head model, and optimizing the texture file of the produced modified head model.

[0227] For example, taking the second model making tool as UE5, that is, after obtaining the Maya source file of the character through the independent Bridge download, the high model of the virtual image exported by RealityCapture can be optimized through ZB, and after exporting the simple model of the head of the virtual image from the Maya source file, the obtained simple model is matched to the high model optimized by ZB, and then, the texture produced by the scan is baked to the simple model by using the baking map method. At the same time, the texture is optimized to improve the quality of the model and the texture, thereby optimizing the head model and the texture.

[0228] Step 6: The optimized head model is added to the original head model through BlendShape;

[0229] Through the above step 6, the optimized head model is added to the original head model through a blending deformation tool, wherein the above blending deformation tool can be a BlendShape tool. Specifically, it includes sub-step 6.1:

[0230] Sub-step 6.1: Scanning texture + MetaHuman texture mixed processing.

[0231] After obtaining the optimized head model and texture, the texture can be scanned and optimized, and the optimized head model can be added to the original head model.

[0232] For example, taking the second model making tool as UE5, after obtaining the optimized head model and texture, the texture can be scanned, and the texture can be processed using MetaHuman editing, and the optimized head model can be added to the original head model.

[0233] Step 7: Export the head model to UE5 and replace the original model.

[0234] Through the above step 7, the added head model and texture file are imported into the above second model making tool, replacing the head model and texture file of the virtual image constructed by the first model making tool, thereby completing the modification of the virtual image of the virtual object.

[0235] For example, taking the second model making tool as UE5, that is, exporting the modified head model to UE5 to replace the original model, specifically, sub-steps 7.1-7.2 are included:

[0236] Sub-step 7.1: Specify DNA and other documents;

[0237] Sub-section 7.2: Associated hair;

[0238] After adding the optimized head model to the original head model through the blend deformation tool, the resulting new head model can be exported to the second model making tool to replace the original model, thereby re-editing the facial features, skin color, body type, hairstyle, clothing, etc. of the virtual image.

[0239] In this way, after the above steps 5 to 7, the virtual image can be adjusted so that the presentation effect of the virtual image reaches the effect expected by the user. Then, it is possible to enter steps 8 to 9, use the motion capture device to obtain the action information of the virtual object to be virtualized, control the virtual image of the virtual object to be virtualized to perform actions matching the action information, and use the Sequence in UE5 to produce a short film about the virtual image of the virtual object to be virtualized.

[0240] Stage 8: Enter the motion capture stage.

[0241] Using a motion capture device to obtain motion information of the virtual object, and controlling the virtual image of the virtual object to perform motions matching the motion information, specifically, including sub-step 8.1:

[0242] Sub-section 8.1: Real-time capture can be performed.

[0243] The electronic device may enter the motion capture phase (i.e., the action capture phase), and while controlling the virtual image of the virtual object to be virtualized to perform actions matching the action information, the virtual image of the virtual object to be virtualized may be motion captured, and after the motion capture, the electronic device may enter phase 9;

[0244] Step 9: Make a short film using Sequence.

[0245] Through the short film production module provided in the second model production tool, a short film of the object to be virtualized is produced based on the movements captured in the above-mentioned motion capture link.

[0246] For example, if the second model making tool is UE5, the short film making module may be a Sequence tool, that is, a short film about the virtual image of the virtual object to be virtualized is made using Sequence in UE5.

[0247] Corresponding to the virtual image creation method provided in the above-mentioned embodiment of the present application, the embodiment of the present application also provides a virtual image creation device.

[0248] Fig. 9 A schematic diagram of the structure of a virtual image creation device provided in an embodiment of the present application is shown in FIG. Fig. 9 As shown, the device may include the following modules:

[0249] A facial image acquisition module 910 is used to acquire multiple facial images of the virtual object collected from multiple angles;

[0250] A construction module 920, configured to construct a head model of the object to be virtualized and a texture file of the head model based on the multiple facial images using a first model making tool;

[0251] The target file acquisition module 930 is used to convert the head model and the texture file into an editable file of a specified format by using the model editing plug-in provided in the second model making tool, and to acquire a target file of the virtual image of the virtual object to be virtualized obtained by editing the editable file;

[0252] The virtual image creation module 940 is used to create a virtual image of the object to be virtualized based on the target file by using the second model making tool.

[0253] As can be seen from the above, by applying the solution provided in the embodiment of the present application, when creating a virtual image, multiple facial images of the object to be virtualized collected from multiple angles can be obtained. Therefore, after obtaining the multiple facial images, the first model making tool is used to construct the head model to be virtualized and the texture file of the head model based on the multiple facial images. Then, the model editing plug-in set in the second model making tool can be used to convert the head model and the texture file into editable files of a specified format. Thus, the target file of the virtual image to be virtualized obtained by editing the editable file can be obtained. In this way, the second model making tool can be used to create the virtual image of the object to be virtualized based on the target file.

[0254] Based on this, by using the solution provided by the embodiment of the present application, the head model of the object to be virtualized is produced by using the acquired facial images of the object to be virtualized at multiple angles, which can shorten the production cycle of the head model, and the virtual image of the object to be virtualized is constructed and edited by using multiple model production tools, thereby improving the efficiency of creating the virtual image. In addition, by using the above-mentioned facial images to produce the head model of the object to be virtualized and the texture file of the head model, the facial features and skin condition of the object to be virtualized can be truly restored, thereby making the produced virtual image more close to the real image of the object to be virtualized.

[0255] Optionally, in a specific implementation, the device further includes:

[0256] An image processing module is used to perform preset image processing on the multiple facial images respectively to obtain multiple target images before constructing the head model of the virtual object and the texture file of the head model based on the multiple facial images using the first model making tool; wherein the preset image processing includes: highlight removal processing and / or shadow removal processing;

[0257] The construction module 920 is specifically used for:

[0258] A first model making tool is used to construct a head model of the object to be virtualized and a texture file of the head model based on the multiple target images.

[0259] Optionally, in a specific implementation, the construction module 920 is specifically used to:

[0260] When a first import instruction about the plurality of facial images is detected, the plurality of facial images are imported into a first model making tool, so that the first model making tool aligns the plurality of facial images according to the angle relationship between the facial images, and uses the aligned plurality of facial images to construct a head model of the object to be virtualized and a texture file of the head model;

[0261] When a first export instruction regarding the head model and the texture file is detected, the head model and the texture file are exported from the first model making tool.

[0262] Optionally, in a specific implementation, the target file acquisition module 930 is specifically used to:

[0263] When a second import instruction regarding the head model and the texture file is detected, the head model and the texture file are imported into a second model making tool, so that a model editing plug-in provided in the second model making tool converts the head model and the texture file into editable files in a specified format, and uploads the editable files to a virtual image creation website corresponding to the model editing plug-in, so that the virtual image creation website generates a target file of the virtual image of the object to be virtualized based on the editing operation on the editable files;

[0264] When a download instruction for the target file is detected, the target file is downloaded from the avatar creation website to the second model making tool using a download plug-in provided in the second model making tool.

[0265] Optionally, in a specific implementation, the device further includes:

[0266] The file replacement module is used to download the target file from the virtual image creation website using a download tool; modify the target file downloaded using the download tool to obtain a modified file; and when a third import instruction regarding the modified file is detected, replace the target file in the second model making tool with the modified file.

[0267] Optionally, in a specific implementation, the device further includes:

[0268] A motion capture module, used to obtain motion information of the virtual object in motion captured by a motion capture device;

[0269] An action control module is used to use the second model making tool to control the virtual image to perform an action matching the action information based on the action information.

[0270] Corresponding to the method for creating a virtual image provided in the above embodiment of the present application, the embodiment of the present application also provides an electronic device, such as Fig.10 As shown, it includes a processor 1001, a communication interface 1002, a memory 1003 and a communication bus 1004, wherein the processor 1001, the communication interface 1002, and the memory 1003 communicate with each other through the communication bus 1004.

[0271] Memory 1003, used for storing computer programs;

[0272] The processor 1001 is used to implement the steps of any virtual image creation method provided in the above-mentioned embodiments of the present application when executing the program stored in the memory 1003.

[0273] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0274] The communication interface is used for communication between the above electronic device and other devices.

[0275] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0276] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0277] In another embodiment provided in the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned virtual image creation methods are implemented.

[0278] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any of the virtual image creation methods in the above embodiments.

[0279] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0280] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0281] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, electronic device embodiment, computer-readable storage medium embodiment, and computer program product embodiment, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0282] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A method for creating a virtual image, characterized in that: Applied to electronic equipment, the method comprises: Acquire multiple facial images of the object to be virtualized collected from multiple angles; Using a first model making tool, based on the multiple facial images, construct a head model of the object to be virtualized and a texture file of the head model; Using a model editing plug-in provided in the second model making tool, the head model and the texture file are converted into editable files of a specified format, and a target file of the virtual image of the object to be virtualized is obtained by editing the editable file; The second model making tool is used to create a virtual image of the object to be virtualized based on the target file.

2. The method according to claim 1, characterized in that Before using the first model making tool to construct the head model of the to-be-virtualized object and the texture file of the head model based on the multiple facial images, the method further includes: Performing preset image processing on the multiple facial images respectively to obtain multiple target images; wherein the preset image processing includes: highlight removal processing and / or shadow removal processing; The step of using the first model making tool to construct the head model of the object to be virtualized and the texture file of the head model based on the multiple facial images includes: A first model making tool is used to construct a head model of the object to be virtualized and a texture file of the head model based on the multiple target images.

3. The method according to claim 1, characterized in that The step of using the first model making tool to construct the head model of the object to be virtualized and the texture file of the head model based on the multiple facial images includes: When a first import instruction about the plurality of facial images is detected, the plurality of facial images are imported into a first model making tool, so that the first model making tool aligns the plurality of facial images according to the angle relationship between the facial images, and uses the aligned plurality of facial images to construct a head model of the object to be virtualized and a texture file of the head model; When a first export instruction regarding the head model and the texture file is detected, the head model and the texture file are exported from the first model making tool.

4. The method according to claim 1, characterized in that: The step of using a model editing plug-in provided in the second model making tool to convert the head model and the texture file into an editable file in a specified format, and obtaining a target file of the virtual image of the object to be virtualized obtained by editing the editable file, comprises: When a second import instruction regarding the head model and the texture file is detected, the head model and the texture file are imported into a second model making tool, so that a model editing plug-in provided in the second model making tool converts the head model and the texture file into editable files in a specified format, and uploads the editable files to a virtual image creation website corresponding to the model editing plug-in, so that the virtual image creation website generates a target file of the virtual image of the object to be virtualized based on the editing operation on the editable files; When a download instruction for the target file is detected, the target file is downloaded from the avatar creation website to the second model making tool using a download plug-in provided in the second model making tool.

5. The method according to claim 4, characterized in that The method further comprises: Downloading the target file from the avatar creation website using a download tool; Modifying the target file downloaded by using the download tool to obtain a modified file; When a third import instruction regarding the modified file is detected, the target file in the second model making tool is replaced with the modified file.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Acquiring motion information of the virtual object in motion captured by a motion capture device; The second model making tool is used to control the virtual image to perform an action matching the action information based on the action information.

7. A virtual image creation device, characterized in that: Applied to electronic equipment, the device comprises: A facial image acquisition module, used to acquire multiple facial images of the virtual object collected from multiple angles; A construction module, configured to construct a head model of the object to be virtualized and a texture file of the head model based on the multiple facial images using a first model making tool; a target file acquisition module, used to convert the head model and the texture file into editable files of a specified format by using a model editing plug-in provided in the second model making tool, and to acquire a target file of the virtual image of the object to be virtualized obtained by editing the editable file; The virtual image creation module is used to use the second model making tool to create a virtual image of the object to be virtualized based on the target file.

8. The device according to claim 7, characterized in that The device also includes: An image processing module is used to perform preset image processing on the multiple facial images respectively to obtain multiple target images before constructing the head model of the virtual object and the texture file of the head model based on the multiple facial images using the first model making tool; wherein the preset image processing includes: highlight removal processing and / or shadow removal processing; The building blocks are specifically used for: A first model making tool is used to construct a head model of the object to be virtualized and a texture file of the head model based on the multiple target images.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 6 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 6 are implemented.

Images