Method and system for creating a character model

Abstract

The embodiment of the present application provides a role model manufacturing method and device, wherein the method comprises the following steps: obtaining a role image input by a user; performing segmentation processing on the role image to obtain a plurality of layer files; searching a target model matched with the plurality of layer files; wherein the target model file has a deformation parameter corresponding to each body; performing deformation processing on the plurality of layer files according to the deformation parameter to generate a role model with a three-dimensional dynamic effect. Thus, the user only needs to provide an image to realize the manufacturing of a Live 2D model, greatly reduces the use cost and threshold of the Live 2D model, and can obtain a role model with a required effect without any related technical knowledge and experience, thereby improving the manufacturing efficiency of the role model.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, system, computer device, and computer-readable storage medium for creating character models. Background Technology

[0002] In existing technologies, Live2D technology is widely used in game and animation video production, virtual live streaming, and other scenarios. The creation of Live2D models is usually done by artists using drawing tools (such as Photoshop) to draw pre-layered images. To facilitate subsequent use in the Live2D Editor, each layer can be moved individually. Then, the Live2D Editor tool is used to design deformers for each layer, and the movement of parts is achieved by arranging the positions of the meshes, rendering the three-dimensional dynamic effect of the Live2D model.

[0003] However, since Live2D models require pre-drawn character images and then imported into Live2D modeling tools for deformation creation, the production process is generally done manually, resulting in high production costs and requiring professional knowledge and skills to create attractive Live2D models. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, computer device, and computer-readable storage medium for creating character models, in order to solve the following problems: the production cost of Live2D models is relatively high, and a certain level of drawing skills and software editing ability is required, resulting in a high barrier to entry.

[0005] One aspect of this application provides a method for creating a character model, including:

[0006] Get the character image input by the user;

[0007] The character image is segmented to obtain multiple layer files;

[0008] Locate a target model file that matches the plurality of layer files; wherein the target model file has deformation parameters corresponding to each body;

[0009] The deformation parameters are used to deform the multiple layer files to generate a character model with a three-dimensional dynamic effect.

[0010] Optionally, each layer file corresponds to a different part of the character's body; the segmentation of the character image to obtain multiple layer files includes:

[0011] The character image is segmented according to different parts of the character's body to obtain the multiple layer files.

[0012] Optionally, the step of segmenting the character image according to different parts of the character's body to obtain the multiple layer files includes:

[0013] Using a preset image processing model, the character image is segmented according to different parts of the character's body to obtain multiple layer files. The occluded areas in the multiple layer files are determined, and the occluded areas are pixel-completed.

[0014] Optionally, before the step of segmenting the character image to obtain multiple layer files, the method further includes:

[0015] Obtain the sample image and the corresponding layer file of the sample image;

[0016] The initial image processing model is trained based on the sample images and the layer files to obtain the preset image processing model.

[0017] Optionally, finding a target model file that matches the plurality of layer files includes:

[0018] Determine the matching degree between the multiple layer files and the multiple preset model files respectively;

[0019] The model file with the highest matching degree is determined as the target model file.

[0020] Optionally, the character model is a Live2D model.

[0021] One aspect of this application provides a character model creation apparatus, comprising:

[0022] The character image acquisition module is used to acquire the character image input by the user;

[0023] The image processing module is used to segment the character image to obtain multiple layer files;

[0024] The model matching module is used to find target model files that match the multiple layer files; wherein, the target model file has deformation parameters corresponding to each body.

[0025] The deformation processing module is used to perform deformation processing on the multiple layer files according to the deformation parameters to generate a character model with three-dimensional dynamic effects.

[0026] Optionally, each layer file corresponds to a different part of the character's torso; the image processing module includes:

[0027] The image processing submodule is used to segment the character image according to different parts of the character's body to obtain the multiple layer files.

[0028] Optionally, the image processing submodule includes:

[0029] The image processing unit is used to segment the character image according to different parts of the character's body using a preset image processing model to obtain multiple layer files, determine the occluded areas in the multiple layer files, and perform pixel completion on the occluded areas.

[0030] Optionally, the device further includes:

[0031] The sample image acquisition module is used to acquire sample images and the layer files corresponding to the sample images;

[0032] The model training module is used to train the initial image processing model based on the sample images and the layer files to obtain the preset image processing model.

[0033] Optionally, the model matching module includes:

[0034] The matching degree determination module is used to determine the matching degree between the multiple layer files and the multiple preset model files respectively;

[0035] The model file determination module is used to determine the model file with the highest matching degree as the target model file.

[0036] Optionally, the character model is a Live2D model.

[0037] One aspect of this application provides a computer device, the computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the character model creation method described above.

[0038] Another aspect of this application provides a computer-readable storage medium storing a computer program that can be executed by at least one processor to implement the steps of the character model creation method described above when the at least one processor executes the computer program.

[0039] The method, system, device, and computer-readable storage medium for creating character models provided in this application embodiment involve: acquiring a character image input by a user; segmenting the character image to obtain multiple layer files; searching for a target model matching the multiple layer files; wherein the target model file has deformation parameters corresponding to each body part; and performing deformation processing on the multiple layer files according to the deformation parameters to generate a character model with a three-dimensional dynamic effect. Thus, users only need to provide one image to create a Live 2D model, greatly reducing the cost and barrier to entry for using Live 2D models. No related technical knowledge or experience is required to obtain the desired character model, improving the efficiency of character model creation. Attached Figure Description

[0040] Figure 1 The diagram illustrates an application environment for a method of creating a character model according to an embodiment of this application.

[0041] Figure 2 A flowchart illustrating a method for creating a character model according to Embodiment 1 of this application is shown schematically;

[0042] Figure 3 The schematic diagram illustrates a framework diagram of a method for creating a character model according to Embodiment 1 of this application;

[0043] Figure 4 A block diagram schematically illustrates an apparatus for creating a character model according to Embodiment 2 of this application; and

[0044] Figure 5 The illustration shows a schematic diagram of the hardware architecture of a computer device suitable for implementing a method for creating a character model according to Embodiment 3 of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0046] It should be noted that the descriptions involving "first," "second," etc., in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0047] In current technologies, the creation of Live 2D models requires users to have a certain level of drawing skills and software editing abilities. For users with no experience, this requires a learning curve, resulting in high production costs and a high barrier to entry. Therefore, it is necessary to find ways to replace users in the steps of Live 2D model creation, helping to simplify the process, reduce costs, enable rapid creation, and even achieve fully automated Live 2D model creation without any production costs.

[0048] In view of this, this application aims to propose a method for creating character models. Through an automated approach, a Live 2D model is automatically generated based on a user-provided character image (e.g., a cartoon character image) and a pre-trained neural network model. No manual operation is required; the generation is completely automated. For the standardized and procedural steps in the production process, machines can perform the execution, making it easier for users to create and use models. This significantly reduces the cost and barrier to entry for using Live 2D models, allowing users to obtain the desired Live 2D model without any related knowledge or experience. This method can be applied to applications such as video production and live streaming.

[0049] Specifically, the process involves acquiring a character image input by the user; segmenting the character image to obtain multiple layer files; finding a target model that matches the multiple layer files; wherein the target model file has deformation parameters corresponding to each body part; and performing deformation processing on the multiple layer files based on the deformation parameters to generate a character model with a three-dimensional dynamic effect. Thus, users only need to provide one image to create a Live 2D model, greatly reducing the cost and barrier to entry for using Live 2D models. No related technical knowledge or experience is required to obtain the desired character model, improving the efficiency of character model creation.

[0050] This application provides several embodiments to further illustrate the character model production scheme, as detailed below.

[0051] In the description of this application, it should be understood that the numerical labels before the steps do not indicate the order of the steps, but are only used to facilitate the description of this application and to distinguish each step, and therefore should not be construed as a limitation of this application.

[0052] The following is a definition of the terminology used in this application:

[0053] Live 2D: Live 2D is a graphics rendering technology used in video games. It generates a two-dimensional image similar to a three-dimensional model by using a series of continuous images and character modeling. It is very useful for adventure games with an animated style. The downside is that Live 2D model characters cannot turn around significantly. Developers are working on making the technology able to display 360-degree images.

[0054] Figure 1 A schematic diagram illustrating an environmental application according to an embodiment of this application is provided. Figure 1 As shown:

[0055] Computer device 10000 can connect to client 30000 via network 20000.

[0056] Computer device 10000 can provide services such as network debugging or returning the creation results data of the character model to client 30000.

[0057] Computer equipment 10000 may be located in a data center, such as a single site, or distributed across different geographical locations (e.g., multiple sites). Computer equipment 10000 may provide services via one or more networks 20000. Network 20000 includes various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, agent devices, and / or similar devices. Network 20000 may include physical links, such as coaxial cable links, twisted-pair cable links, fiber optic links, combinations thereof, etc. Network 20000 may include wireless links, such as cellular links, satellite links, Wi-Fi links, etc.

[0058] Computer device 10000 can be implemented by one or more compute nodes. One or more compute nodes can include virtualized compute instances. Virtualized compute instances can include virtual machines, such as emulations of computer systems, operating systems, servers, etc. Compute nodes can load virtual machines based on virtual images and / or other data defining specific software used for emulation (e.g., operating systems, dedicated applications, servers). As the demand for different types of processing services changes, different virtual machines can be loaded and / or terminated on one or more compute nodes. A hypervisor can be implemented to manage the use of different virtual machines on the same compute node.

[0059] Client 30000 can be configured to access the content and services of computer device 10000. Client 30000 can include any type of electronic device, such as mobile devices, tablets, laptops, workstations, virtual reality devices, gaming devices, set-top boxes, digital streaming media devices, vehicle terminals, smart TVs, etc.

[0060] The client 30000 can output (e.g., display, render, present) the production results data of the character model to the user.

[0061] The following will describe a network debugging solution through several embodiments. This solution can be implemented using computer equipment 10000.

[0062] Example 1

[0063] Figure 2 A flowchart illustrating a method for creating a character model according to Embodiment 1 of this application is shown. It includes steps S200-S206, wherein...

[0064] Step S200: Obtain the character image input by the user;

[0065] The character image can be an image of an anime character or a character from a game, etc., and this embodiment does not impose specific limitations on this. In this embodiment, the character image can be manually entered and uploaded by the user. A user interface is provided on the client, which includes an entry point for uploading character images, for inputting and uploading character images.

[0066] Step S202: The character image is segmented to obtain multiple layer files;

[0067] In this embodiment, the character image can be segmented using some algorithm models to obtain multiple layer files. Each layer file can correspond to various parts of the character's body, such as the left eye, right eye, left eyebrow, right eyebrow, upper lip, lower lip, front hair, back hair, legs, etc. Each part of the character's body has a corresponding layer file, so that each part of the character's body can be moved individually.

[0068] In the actual implementation, since some body parts in the segmented layer file may be obscured by other parts, pixel completion can be performed on the obscured parts to obtain a complete layer file, thus avoiding pixel loss during the movement process.

[0069] Step S204: Locate a target model that matches the plurality of layer files; wherein the target model file has deformation parameters corresponding to each body part;

[0070] In this embodiment, a Live 2D model library can be pre-established. Each model file in this library has deformation parameters corresponding to various body parts. Target model files matching multiple layer files are searched from the Live 2D model library, allowing the deformation parameters of the target model file to be directly applied to the layer files to achieve movement of the character's various body parts. Specifically, the Live 2D model library can be deployed in a Live 2D model creation tool. The processed multiple layer files are imported into the Live 2D model creation tool, and target model files matching multiple layer files are searched from the Live 2D model library.

[0071] Step S206: Perform deformation processing on the multiple layer files according to the deformation parameters to generate a character model with three-dimensional dynamic effects.

[0072] In this embodiment, the deformation parameters corresponding to each body part in the target model file are used as deformers and applied to multiple layer files to drive the various body parts of the character in the multiple layer files to perform deformation operations such as movement or rotation, thereby generating a character model with three-dimensional dynamic effects.

[0073] In practical implementation, simple position matching can be performed on the body parts in the target model file and layer file to adapt the existing deformation parameters in the target model file. This allows the deformer of the target model file to be applied to the target model, enabling the movement of each body part of the character model. The character model can be a Live2D model; therefore, the user only needs to provide a single character image to create a Live2D model.

[0074] The following are several optional embodiments for optimizing the method of creating the character model, as follows:

[0075] In a preferred embodiment of this application, each layer file corresponds to a different part of the character's body; step S202 may include the following steps: segmenting the character image according to different parts of the character's body to obtain the multiple layer files.

[0076] By segmenting the character image according to different body parts, layer files are obtained, which are divided into layers according to body parts, so that each body part of the character can be moved individually. The layer files can be in PSD format.

[0077] In a preferred embodiment of this application, the step of segmenting the character image according to different parts of the character's body to obtain the multiple layer files may include the following steps: segmenting the character image according to different parts of the character's body using a preset image processing model to obtain multiple layer files, determining the occluded areas in the multiple layer files, and performing pixel completion on the occluded areas.

[0078] The preset image processing model is a pre-trained convolutional neural network model, which includes two functions: image segmentation and pixel completion. In this embodiment, the character image is input into the preset image processing model for segmentation and pixel completion, and multiple layer files are output. The preset image processing model can segment the character image according to different parts of the character's body to obtain multiple layer files, identify the occluded areas in the multiple layer files, and perform pixel completion on the occluded areas.

[0079] In a preferred embodiment of this application, before the step of segmenting the character image to obtain multiple layer files, the method further includes: acquiring a sample image and the layer file corresponding to the sample image; and training an initial image processing model based on the sample image and the layer file to obtain the preset image processing model.

[0080] In this embodiment, sample images and their corresponding layer files are acquired, and an initial image processing model is trained based on these images and layer files to obtain a pre-defined image processing model. As an example, 1000 sets of Live 2D model images and their corresponding PSD files can be collected as samples to train a CNN network model. This CNN network includes two functions: segmentation and image completion. The segmentation function divides the character image into various body parts, such as the left eyebrow, right eyebrow, upper lip, lower lip, front hair, back hair, and legs. Because some body parts may be occluded by other parts, a pixel completion function is also included to ensure the integrity of the obtained layered files. During training, the L2 loss function can be used for model supervision until the model converges as expected, at which point the trained model is output.

[0081] In a preferred embodiment of this application, the step of finding a target model file that matches the plurality of layer files includes the following steps: determining the matching degree between the plurality of layer files and the plurality of preset model files respectively; and determining the model file with the highest matching degree as the target model file.

[0082] In this embodiment, a Live 2D model library is pre-established, in which each model file has deformation parameters corresponding to each body part. The matching degree between the layer file and each preset model file in the Live 2D model library is determined, and then the model file with the highest matching degree is selected as the target model file.

[0083] In this embodiment, a character image input by the user is acquired; the character image is segmented to obtain multiple layer files; a target model matching the multiple layer files is found; wherein, the target model file has deformation parameters corresponding to each body part; the multiple layer files are deformed according to the deformation parameters to generate a character model with a three-dimensional dynamic effect. Thus, the user only needs to provide one image to create a Live 2D model, greatly reducing the cost and barrier to entry for using Live 2D models. No related technical knowledge or experience is required to obtain the character model with the desired effect, improving the efficiency of character model creation.

[0084] To further describe the character model creation scheme of this embodiment, such as Figure 3 The diagram illustrates a framework that includes two processing steps: image conversion to layers and layer deformation matching. The data processing is as follows: The image conversion to layers step receives an image uploaded by the user and processes it using a segmentation model and a model completion (pixel padding) to obtain a PSD layer file. The layer deformation matching step uses a Live 2D database to perform model matching to obtain a Live 2D template file. The deformation function of the Live 2D template file is then applied to the PSD layer file for template matching engine processing, resulting in the final required Live 2D model file.

[0085] Example 2

[0086] Figure 4 The diagram schematically illustrates a block diagram of a character model creation apparatus according to Embodiment 2 of this application. This apparatus can be divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiment of this application. The program module referred to in this embodiment is a series of computer program instruction segments capable of performing a specific function. The following description will specifically introduce the functions of each program module in the embodiments of this application.

[0087] like Figure 4 As shown, the character model manufacturing device 400 may include the following modules:

[0088] The character image acquisition module 410 is used to acquire the character image input by the user.

[0089] Image processing module 420 is used to segment the character image to obtain multiple layer files;

[0090] The model matching module 430 is used to find a target model file that matches the plurality of layer files; wherein the target model file has deformation parameters corresponding to each body.

[0091] The deformation processing module 440 is used to perform deformation processing on the multiple layer files according to the deformation parameters to generate a character model with three-dimensional dynamic effects.

[0092] In a preferred embodiment of this application, each layer file corresponds to a different part of the character's torso; the image processing module 420 includes:

[0093] The image processing submodule is used to segment the character image according to different parts of the character's body to obtain the multiple layer files.

[0094] In a preferred embodiment of this application, the image processing submodule includes:

[0095] The image processing unit is used to segment the character image according to different parts of the character's body using a preset image processing model to obtain multiple layer files, determine the occluded areas in the multiple layer files, and perform pixel completion on the occluded areas.

[0096] In a preferred embodiment of this application, the apparatus further includes:

[0097] The sample image acquisition module is used to acquire sample images and the layer files corresponding to the sample images;

[0098] The model training module is used to train the initial image processing model based on the sample images and the layer files to obtain the preset image processing model.

[0099] In a preferred embodiment of this application, the model matching module 430 includes:

[0100] The matching degree determination module is used to determine the matching degree between the multiple layer files and the multiple preset model files respectively;

[0101] The model file determination module is used to determine the model file with the highest matching degree as the target model file.

[0102] In a preferred embodiment of this application, the character model is a Live2D model.

[0103] Example 3

[0104] Figure 5 This illustration schematically shows a hardware architecture diagram of a computer device 10000 suitable for implementing a method for creating a character model according to Embodiment 3 of this application. In this embodiment, the computer device 10000 is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. For example, it may be a smartphone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server, or cabinet server (including standalone FEN servers, or server clusters composed of multiple servers), etc. Figure 5 As shown, the computer device 10000 includes, but is not limited to, at least the following: a memory 10010, a processor 10020, and a network interface 10030 that can communicate and be linked to each other via a system bus. Wherein:

[0105] The memory 10010 includes at least one type of computer-readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 10000, such as the hard disk or memory of the computer device 10000. In other embodiments, the memory 10010 may also be an external storage device of the computer device 10000, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 10000. Of course, the memory 10010 may also include both the internal storage module and the external storage device of the computer device 10000. In this embodiment, the memory 10010 is typically used to store the operating system and various application software installed on the computer device 10000, such as program code for creating character models. In addition, the memory 10010 can also be used to temporarily store various types of data that have been output or will be output.

[0106] In some embodiments, processor 10020 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. Processor 10020 is typically used to control the overall operation of computer device 10000, such as performing control and processing related to data interaction or communication with computer device 10000. In this embodiment, processor 10020 is used to run program code stored in memory 10010 or process data.

[0107] Network interface 10030 may include a wireless network interface or a wired network interface, which is typically used to establish a communication link between computer device 10000 and other computer devices. For example, network interface 10030 is used to connect computer device 10000 to an external terminal via a network, establishing a data transmission channel and communication link between computer device 10000 and the external terminal. The network may be an intranet, the Internet, Global System for Mobile Communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi, or other wireless or wired networks.

[0108] It should be pointed out that, Figure 5 Only computer devices with components 10010-10030 are shown; however, it should be understood that it is not required to implement all of the shown components, and more or fewer components may be implemented instead.

[0109] In this embodiment, the method for creating the character model stored in the memory 10010 can be further divided into one or more program modules and executed by one or more processors (processor 10020 in this embodiment) to complete the embodiment of this application.

[0110] Example 4

[0111] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the character model creation method in the embodiments.

[0112] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device. Of course, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the computer-readable storage medium is typically used to store the operating system and various application software installed on the computer device, such as the program code of the method for creating the character model in the embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or will be output.

[0113] Obviously, those skilled in the art should understand that the modules or steps of the embodiments of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the embodiments of this application are not limited to any particular combination of hardware and software.

[0114] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for creating a character model, characterized in that, include: Get the character image input by the user; The character image is segmented to obtain multiple layer files; Locate a target model file that matches the plurality of layer files; wherein the target model file has deformation parameters corresponding to each body part; wherein each layer file corresponds to a different part of the character's body. Based on the deformation parameters, the deformation process is applied to each body part in the multiple layer files to generate a character model with a three-dimensional dynamic effect. The step of finding a target model file that matches the plurality of layer files includes: Determine the matching degree between the multiple layer files and the multiple preset model files respectively; The model file with the highest matching degree is determined as the target model file.

2. The method for creating a character model according to claim 1, characterized in that, The segmentation process of the character image yields multiple layer files, including: The character image is segmented according to different body parts to obtain multiple layer files.

3. The method for creating a character model according to claim 2, characterized in that, The process of segmenting the character image according to different body parts to obtain the multiple layer files includes: Using a preset image processing model, the character image is segmented according to different parts of the character's body to obtain multiple layer files. The occluded areas in the multiple layer files are determined, and the occluded areas are pixel-completed.

4. The method for creating a character model according to claim 3, characterized in that, Before the step of segmenting the character image to obtain multiple layer files, the method further includes: Obtain the sample image and the corresponding layer file of the sample image; The initial image processing model is trained based on the sample images and the layer files to obtain the preset image processing model.

5. The method for creating a character model according to claim 1, characterized in that, The character model is a Live2D model.

6. A device for creating character models, characterized in that, include: The character image acquisition module is used to acquire the character image input by the user; The image processing module is used to segment the character image to obtain multiple layer files; A model matching module is used to find target model files that match the plurality of layer files; wherein, the target model file has deformation parameters corresponding to each body; wherein, each layer file corresponds to a different part of the character's body; The deformation processing module is used to perform deformation processing on each body part in the multiple layer files according to the deformation parameters as a deformer, so as to generate a character model with three-dimensional dynamic effects. The model matching module is further used for: Determine the matching degree between the multiple layer files and the multiple preset model files respectively; The model file with the highest matching degree is determined as the target model file.

7. The apparatus for creating a character model according to claim 6, characterized in that, Each of the aforementioned layer files corresponds to a different part of the character's body; The image processing module includes: The image processing submodule is used to segment the character image according to different parts of the character's body to obtain the multiple layer files.

8. The apparatus for creating a character model according to claim 7, characterized in that, The image processing submodule includes: The image processing unit is used to segment the character image according to different parts of the character's body using a preset image processing model to obtain multiple layer files, determine the occluded areas in the multiple layer files, and perform pixel completion on the occluded areas.

9. The apparatus for creating a character model according to claim 8, characterized in that, The device further includes: The sample image acquisition module is used to acquire sample images and the layer files corresponding to the sample images; The model training module is used to train the initial image processing model based on the sample images and the layer files to obtain the preset image processing model.

10. The apparatus for creating a character model according to claim 6, characterized in that, The model matching module includes: The matching degree determination module is used to determine the matching degree between the multiple layer files and the multiple preset model files respectively; The model file determination module is used to determine the model file with the highest matching degree as the target model file.

11. The apparatus for creating a character model according to claim 6, characterized in that, The character model is a Live2D model.

12. A computer device, the computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it performs the steps of the method for creating a character model as described in any one of claims 1 to 5.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that can be executed by at least one processor to cause the at least one processor to perform the steps of the method for creating a character model according to any one of claims 1 to 5.

14. A computer program product comprising computer instructions, characterized in that, When executed by a processor, the computer instructions implement the steps of the method for creating a character model as described in any one of claims 1 to 5.

Images