Method and system for driving control of virtual characters

Abstract

The embodiment of the application provides a kind of virtual role drive control method and device, wherein the described method comprises: the image of virtual role is sent to cloud end;Image feature information is returned after the image of virtual role is extracted by cloud end;Corresponding face capture gesture parameter is obtained to the image of user;Determine optical flow feature information according to the image feature information and face capture gesture parameter;Optical flow deformation processing is carried out based on the optical flow feature information, to drive the face of virtual role to change posture.It can be driven by the advantage of the powerful computing capacity of cloud end, capture image feature easy to drive, and the image feature information is issued to mobile terminal by cloud end, and mobile terminal combines face capture gesture parameter to easily realize real-time driving of the face of virtual role.Moreover, user only needs to provide an image, to realize the drive of the face of virtual role, reduce the use threshold of the face of virtual role.

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 driving and controlling virtual characters. Background Technology

[0002] In existing technologies, there are two main solutions for facial recognition of anime characters:

[0003] (1) Using 3D / 2.5D models such as MMD and Live2D for character-driven design has the advantages of fast rendering speed, low computational load, and high-quality results on mobile devices. However, it has the following disadvantages: each model requires professional designers to draw and edit, the audience is small, and if you want to achieve mass production, it will consume a lot of time and manpower.

[0004] (2) Only one image of an anime character's face needs to be input. The character can be driven by a neural network. The advantage of this approach is that it can achieve a certain degree of acceleration through model compression, pruning, etc. It is usually deployed on the GPU of a PC rather than on a mobile device. However, the disadvantage is that it has high hardware requirements for the user's device. It requires a computer with a GPU to process the data, and its popularity is relatively low. Summary of the Invention

[0005] The purpose of this application is to provide a method, system, computer device, and computer-readable storage medium for driving and controlling virtual characters, in order to solve the following problems: how to reduce the production cost of facial driving schemes for anime characters and reduce the consumption of device performance during the driving process.

[0006] One aspect of this application provides a method for driving and controlling a virtual character, including:

[0007] Send images of virtual characters to the cloud;

[0008] Receive image feature information returned by the cloud after extracting features from the image of the virtual character;

[0009] Obtain the face capture pose parameters corresponding to the user image;

[0010] Optical flow feature information is determined based on the image feature information and the surface capture pose parameters;

[0011] Optical flow deformation processing is performed based on the optical flow feature information to drive the virtual character's face to change pose.

[0012] Optionally, determining the optical flow feature information based on the image feature information and the surface capture pose parameters includes:

[0013] The image feature information and the surface capture pose parameters are subjected to matrix multiplication to determine the optical flow feature information.

[0014] Optionally, obtaining the face capture pose parameters corresponding to the user image includes:

[0015] Real-time acquisition of face capture pose parameters corresponding to the user's image; or,

[0016] Acquire the face capture pose parameters corresponding to the user image according to a preset period.

[0017] Optionally, obtaining the face capture pose parameters corresponding to the user image includes:

[0018] Acquire user images captured by camera equipment;

[0019] The user image is identified to obtain the face capture pose parameters.

[0020] Optionally, before the step of sending the image of the virtual character input by the user to the cloud, the method further includes:

[0021] A pre-set image processing model is deployed in the cloud; the pre-set image processing model is used to extract features from the image of the virtual character to obtain image feature information.

[0022] One aspect of this application provides a driving control device for a virtual character, comprising:

[0023] The image sending module is used to send images of virtual characters to the cloud;

[0024] The image feature receiving module is used to receive image feature information returned by the cloud after extracting features from the image of the virtual character;

[0025] The face capture pose acquisition module is used to acquire the face capture pose parameters corresponding to the user image;

[0026] An optical flow feature determination module is used to determine optical flow feature information based on the image feature information and the surface capture pose parameters;

[0027] The optical flow deformation processing module is used to perform optical flow deformation processing based on the optical flow feature information to drive the virtual character's face to change pose.

[0028] Optionally, the optical flow feature determination module includes:

[0029] The matrix multiplication processing submodule is used to perform matrix multiplication processing on the image feature information and the surface capture pose parameters to determine the optical flow feature information.

[0030] Optionally, the face capture pose acquisition module includes:

[0031] The first pose acquisition submodule is used to acquire the face capture pose parameters corresponding to the user image in real time; or,

[0032] The second pose acquisition submodule is used to acquire the face capture pose parameters corresponding to the user image according to a preset period.

[0033] Optionally, the face capture pose acquisition module includes:

[0034] The user image acquisition submodule is used to acquire user images captured by the camera device;

[0035] The pose recognition submodule is used to recognize the user image to obtain the face capture pose parameters.

[0036] Optionally, the device further includes:

[0037] The model deployment module is used to deploy a pre-set image processing model in the cloud; the pre-set image processing model is used to extract features from the image of the virtual character to obtain image feature information.

[0038] 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 virtual character driving control method as described above.

[0039] One 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 virtual character driving control method described above when the at least one processor executes the computer program.

[0040] The virtual character driving control method, system, device, and computer-readable storage medium provided in this application embodiment transmit the image of the virtual character to the cloud; receive image feature information returned by the cloud after feature extraction of the virtual character image; obtain face capture pose parameters corresponding to the user image; determine optical flow feature information based on the image feature information and face capture pose parameters; and perform optical flow deformation processing based on the optical flow feature information to drive the virtual character's face to change pose. This leverages the powerful computing capabilities of the cloud to capture easily driven image features, transmits image feature information from the cloud to the mobile terminal, and the mobile terminal, combined with face capture pose parameters, easily achieves real-time driving of the virtual character's face. Furthermore, the user only needs to provide one image to drive the virtual character's face, lowering the barrier to entry for virtual character face driving, enabling easy batch production, and saving time and labor costs associated with the production process. Attached Figure Description

[0041] Figure 1 This diagram schematically illustrates an application environment of a virtual character driving control method according to an embodiment of this application.

[0042] Figure 2 A flowchart illustrating a driving control method for a virtual character according to Embodiment 1 of this application is shown schematically.

[0043] Figure 3 The illustration shows a schematic diagram of a character image according to Embodiment 1 of this application;

[0044] Figure 4 The schematic diagram illustrates the framework of the driving control method for a virtual character according to Embodiment 1 of this application;

[0045] Figure 5 A block diagram schematically illustrates a drive control device for a virtual character according to Embodiment 2 of this application; and

[0046] Figure 6 The illustration shows a schematic diagram of the hardware architecture of a computer device suitable for implementing a driving control method for virtual characters according to Embodiment 3 of this application. Detailed Implementation

[0047] 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.

[0048] 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.

[0049] Existing technologies using 3D / 2.5D models such as MMD and Live2D for character-driven design require professional designers to create and edit each model, limiting the target audience. Mass production of these models also incurs significant time and manpower costs. While solutions that only require a single image of an anime character's face and utilize neural networks for character-driven design have higher hardware requirements, necessitating computers with GPUs, thus limiting their widespread adoption.

[0050] Furthermore, while deep learning possesses powerful learning capabilities, even enabling the generation and editing of high-quality images, generation tasks typically employ large model parameters, requiring large machine platforms, such as servers, with thousands of GPUs for parallel processing during training. To enable operation on mobile platforms, the industry has undertaken extensive work, including pruning, compressing, and retraining the model, as well as employing more complex techniques, such as reinforcement learning, to achieve a smaller model.

[0051] In view of this, this application aims to propose a method for driving and controlling a virtual character. This method involves sending an image of the virtual character to the cloud; receiving image feature information returned by the cloud after feature extraction of the virtual character image; obtaining facial capture pose parameters corresponding to the user's image; determining optical flow feature information based on the image feature information and the facial capture pose parameters; and performing optical flow deformation processing based on the optical flow feature information to drive the virtual character's face to change pose. This leverages the powerful computing capabilities of the cloud to capture easily driven image features. The image feature information is then sent from the cloud to a mobile device, which, combined with the facial capture pose parameters, easily achieves real-time driving of the virtual character's face. Furthermore, the user only needs to provide one image to drive the virtual character's face, lowering the barrier to entry for virtual character face driving and enabling easy batch production, saving time and manpower costs associated with the production process.

[0052] This application provides several embodiments to further illustrate the driving control scheme for virtual characters, as detailed below.

[0053] 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.

[0054] The following is a definition of the terminology used in this application:

[0055] MMD: MikuMikuDance, abbreviated as MMD, also known as Future Dance or Moe Moe Da, is a free 3D animation creation program. It uses other 3D modeling software to create 3D models of VOCALOID virtual singers such as Hatsune Miku, and then imports them into MikuMikuDance for animation production. "MMD" is also used to refer to animations created with this software.

[0056] Live2D: Live2D 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 Live2D characters cannot turn around significantly. Developers are working on making the technology able to display 360-degree images.

[0057] GPU: Graphics Processing Unit (GPU), also known as display core, visual processor, or display chip, is a microprocessor specifically designed for performing image and graphics-related calculations on personal computers, workstations, game consoles, and some mobile devices (such as tablets and smartphones).

[0058] CPU: Central Processing Unit (CPU) is the core of a computer system for computation and control, and is the final execution unit for information processing and program execution. Since its inception, the CPU has made tremendous progress in logical structure, operating efficiency, and functional extension.

[0059] FPS: Frames Per Second (FPS) is a definition in the field of graphics, referring to the number of frames in an animation or video. FPS measures the amount of information used to store and display moving video. The higher the frame rate, the smoother the displayed motion. Generally, a minimum of 30 frames per second is considered ideal to avoid choppy motion. Some computer video formats can only provide 15 frames per second.

[0060] Figure 1 The illustration shows an environmental application diagram according to an embodiment of this application. For example... Figure 1 As shown:

[0061] Computer device 10000 can connect to client 30000 via network 20000.

[0062] Computer device 10000 can provide services such as network debugging or returning the driver control result data of the virtual character to client 30000.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] The client 30000 can output (e.g., display, render, present) the driving control results data of the virtual character to the user.

[0067] The following will describe a network debugging solution through several embodiments. This solution can be implemented using computer equipment 10000.

[0068] Example 1

[0069] Figure 2A flowchart illustrating a driving control method for a virtual character according to Embodiment 1 of this application is shown schematically. It includes steps S200-S208, wherein...

[0070] Step S200: Send the image of the virtual character to the cloud;

[0071] The image of the virtual character can be an image of an anime character, or an image of a character from a game, etc., and this embodiment does not impose specific limitations on this. As an example, the image of the virtual character is as follows: Figure 3 The image shown is of an anime character.

[0072] In this embodiment, the image of the virtual character can be manually entered and uploaded by the user. A user interface is provided on the client, containing an image upload entry for inputting the virtual character's image. The client can detect the user's action of inputting and uploading an image through the image upload entry and, in response, send the virtual character's image to the cloud to utilize the cloud's powerful computing capabilities for feature extraction.

[0073] Step S202: Receive image feature information returned by the cloud after extracting features from the image of the virtual character;

[0074] In this embodiment, after receiving the image of the virtual character uploaded by the user through the client, the cloud utilizes its powerful computing capabilities to extract features from the image. The extracted image feature information is then returned to the client, thus transferring the feature extraction process from the client's local storage to the cloud. This accelerates image processing and reduces the performance consumption of the device with the client installed. The image feature information obtained through cloud-based feature extraction contains all the deformation information required to drive the virtual character's image to any facial pose parameter. Therefore, this image feature information can be used to drive the virtual character's face to any pose.

[0075] Step S204: Obtain the face capture pose parameters corresponding to the user image;

[0076] The user image is an image captured by a camera device targeting the user. This image contains the facial region, and facial pose parameters can be obtained based on the facial region. Facial pose parameters characterize facial expressions, posture, and orientation. Specifically, camera devices are typically deployed on the user's device to capture user images, and facial pose parameters are derived from these images through analysis.

[0077] In one implementation, the facial pose parameters corresponding to the user's image can be acquired in real time, so that the virtual character's face can be driven to change poses in real time based on these facial pose parameters. In another implementation, since the frequency of user's facial pose changes is not high, in order to further reduce the computational load on the client, the facial pose parameters corresponding to the user's image can be acquired periodically according to a preset period, so that the virtual character's face can be driven to change poses continuously based on these facial pose parameters. For example, if the preset period is 1 second or 5 seconds, then the facial pose parameters corresponding to the user's image can be acquired every 1 second or 5 seconds.

[0078] Step S206: Determine optical flow feature information based on the image feature information and the surface capture pose parameters;

[0079] Among them, optical flow feature information is used to express the apparent motion of image brightness.

[0080] In one example, optical flow features can be determined based on image features and surface capture pose parameters using matrix multiplication.

[0081] Step S208: Perform optical flow deformation processing based on the optical flow feature information to drive the virtual character's face to change pose.

[0082] In this embodiment, after calculating the optical flow feature information, optical flow deformation processing can be performed based on the optical flow feature information to drive the virtual character's face to change its posture, thereby controlling the virtual character's face to present a posture effect that matches the user's facial posture.

[0083] The following are several optional embodiments for optimizing the drive control method of the virtual character, as follows:

[0084] In a preferred embodiment of this application, step S206 may specifically include the following steps:

[0085] The image feature information and the surface capture pose parameters are subjected to matrix multiplication to determine the optical flow feature information.

[0086] In this embodiment, the optical flow feature information is determined by performing matrix multiplication on the image feature information and the surface capture pose parameters. Multiple features in the image feature information are multiplied by the surface capture pose parameters, and the results are weighted and summed.

[0087] In a preferred embodiment of this application, the image feature information includes all the deformation information required to drive the virtual character image to all face capture pose parameters.

[0088] In a preferred embodiment of this application, step S204 may include the following steps: acquiring face capture pose parameters corresponding to the user image in real time; or acquiring face capture pose parameters corresponding to the user image according to a preset period.

[0089] In one implementation, the facial capture pose parameters corresponding to the user's image can be obtained in real time, so as to drive the virtual character's face to change pose in real time based on the facial capture pose parameters.

[0090] In another implementation, since the frequency of user facial pose changes is not high, in order to further reduce the computational load on the client, the facial pose parameters corresponding to the user image can be acquired periodically according to a preset period, so as to continuously drive the virtual character's face to change poses based on the facial pose parameters. The preset period is a pre-set interval time length, for example, the preset period is 1 second or 5 seconds, then the facial pose parameters corresponding to the user image are reacquired every 1 second or 5 seconds. The preset period can be flexibly set according to actual needs, and this embodiment does not impose specific restrictions on it.

[0091] In a preferred embodiment of this application, step S204 may include the following steps: acquiring a user image captured by a camera device; and recognizing the user image to obtain the face capture posture parameters.

[0092] In this embodiment, the client can call the camera device deployed in the terminal device to capture user images, and use a facial pose recognition algorithm to identify the user images to obtain facial pose parameters. As an example, facial pose estimation algorithm can be used to identify facial pose parameters, but this embodiment does not impose any specific limitations on this.

[0093] In a preferred embodiment of this application, before the step of sending the image of the virtual character input by the user to the cloud, the method further includes:

[0094] A pre-set image processing model is deployed in the cloud; the pre-set image processing model is used to extract features from the image of the virtual character to obtain image feature information.

[0095] The preset image processing model is a pre-trained neural network model. By acquiring a large number of sample images and their corresponding image feature information as input, the model is trained based on deep learning technology to obtain the preset image processing model.

[0096] Because the cloud possesses powerful computing capabilities, complex calculations can be transferred to the cloud for processing, thereby avoiding processing on the client side and reducing the performance consumption of the terminal devices where the client is deployed. In this embodiment, a pre-built image processing model can be deployed in the cloud to extract image feature information from the image of the virtual character.

[0097] To further describe the driving control scheme of the virtual character in this embodiment, such as Figure 4 The diagram illustrates a framework comprising two processing components: a cloud-based (GPU deployment) system and a mobile-based (CPU deployment) system. The data processing steps are as follows: The user-uploaded image is sent to the cloud via the mobile device. A pre-built image processing model deployed in the cloud processes the image to obtain image features. Simultaneously, the user's camera on the mobile device captures facial parameters, and these parameters are used to determine facial pose parameters. Matrix multiplication of the image features and pose parameters yields specified pose optical flow features. Optical flow deformation processing is then performed based on these features to drive the virtual character's face to undergo pose transformations, thereby controlling the virtual character's face to present a pose effect that matches the user's facial posture.

[0098] Example 2

[0099] Figure 5 The diagram illustrates a block diagram of a virtual character drive control device according to Embodiment 2 of this application. This virtual character drive control device 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 the embodiments of this application refers to 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.

[0100] like Figure 5 As shown, the drive control device 500 for the virtual character may include the following modules:

[0101] Image sending module 510 is used to send images of virtual characters to the cloud;

[0102] Image feature receiving module 520 is used to receive image feature information returned by the cloud after feature extraction of the image of the virtual character;

[0103] The face capture pose acquisition module 530 is used to acquire the face capture pose parameters corresponding to the user image;

[0104] Optical flow feature determination module 540 is used to determine optical flow feature information based on the image feature information and the surface capture pose parameters;

[0105] The optical flow deformation processing module 550 is used to perform optical flow deformation processing based on the optical flow feature information to drive the virtual character's face to change pose.

[0106] In a preferred embodiment of this application, the optical flow feature determination module 540 includes:

[0107] The matrix multiplication processing submodule is used to perform matrix multiplication processing on the image feature information and the surface capture pose parameters to determine the optical flow feature information.

[0108] In a preferred embodiment of this application, the face capture pose acquisition module 530 includes:

[0109] The first pose acquisition submodule is used to acquire the face capture pose parameters corresponding to the user image in real time; or,

[0110] The second pose acquisition submodule is used to acquire the face capture pose parameters corresponding to the user image according to a preset period.

[0111] In a preferred embodiment of this application, the face capture pose acquisition module 530 includes:

[0112] The user image acquisition submodule is used to acquire user images captured by the camera device;

[0113] The pose recognition submodule is used to recognize the user image to obtain the face capture pose parameters.

[0114] In a preferred embodiment of this application, the apparatus further includes:

[0115] The model deployment module is used to deploy a pre-set image processing model in the cloud; the pre-set image processing model is used to extract features from the image of the virtual character to obtain image feature information.

[0116] Example 3

[0117] Figure 6 This illustration schematically shows a hardware architecture diagram of a computer device 10000 suitable for implementing a drive control method for virtual characters 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 can 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 6As 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:

[0118] 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 driving and controlling virtual characters. In addition, the memory 10010 can also be used to temporarily store various types of data that have been output or will be output.

[0119] 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.

[0120] 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.

[0121] It should be pointed out that, Figure 6 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.

[0122] In this embodiment, the virtual character driving control method stored in memory 10010 can also be 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.

[0123] Example 4

[0124] 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 virtual character driving control method in the embodiments.

[0125] 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 driving control method for virtual characters in this 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.

[0126] 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.

[0127] 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 driving and controlling a virtual character, characterized in that, include: Send images of virtual characters to the cloud; Receive image feature information returned by the cloud after extracting features from the image of the virtual character; Obtain the face capture pose parameters corresponding to the user image; Optical flow feature information is determined based on the image feature information and the surface capture pose parameters; Optical flow deformation processing is performed based on the optical flow feature information to drive the virtual character's face to change pose. The image feature information includes all the deformation information required to drive the virtual character's image to all face capture pose parameters, and the image feature information is used to drive the virtual character's face to any pose.

2. The driving control method for virtual characters according to claim 1, characterized in that, The step of determining optical flow feature information based on the image feature information and the surface capture pose parameters includes: The image feature information and the surface capture pose parameters are subjected to matrix multiplication to determine the optical flow feature information.

3. The driving control method for virtual characters according to claim 1, characterized in that, The acquisition of the face capture pose parameters corresponding to the user image includes: Real-time acquisition of face capture pose parameters corresponding to the user's image; or, Acquire the face capture pose parameters corresponding to the user image according to a preset period.

4. The driving control method for virtual characters according to claim 1 or 3, characterized in that, The acquisition of the face capture pose parameters corresponding to the user image includes: Acquire user images captured by camera equipment; The user image is identified to obtain the face capture pose parameters.

5. The driving control method for virtual characters according to claim 1, characterized in that, Prior to the step of sending the image of the virtual character to the cloud, the method also includes: A pre-set image processing model is deployed in the cloud; the pre-set image processing model is used to extract features from the image of the virtual character to obtain image feature information.

6. A drive control device for a virtual character, characterized in that, include: The image sending module is used to send images of virtual characters to the cloud; The image feature receiving module is used to receive image feature information returned by the cloud after extracting features from the image of the virtual character; The face capture pose acquisition module is used to acquire the face capture pose parameters corresponding to the user image; An optical flow feature determination module is used to determine optical flow feature information based on the image feature information and the surface capture pose parameters; The optical flow deformation processing module is used to perform optical flow deformation processing based on the optical flow feature information to drive the virtual character's face to change pose. The image feature information includes all the deformation information required to drive the virtual character's image to all face capture pose parameters, and the image feature information is used to drive the virtual character's face to any pose.

7. The virtual character drive control device according to claim 6, characterized in that, The optical flow feature determination module includes: The matrix multiplication processing submodule is used to perform matrix multiplication processing on the image feature information and the surface capture pose parameters to determine the optical flow feature information.

8. The virtual character drive control device according to claim 6, characterized in that, The face capture pose acquisition module includes: The first pose acquisition submodule is used to acquire the face capture pose parameters corresponding to the user image in real time; or, The second pose acquisition submodule is used to acquire the face capture pose parameters corresponding to the user image according to a preset period.

9. The drive control device for a virtual character according to claim 6 or 8, characterized in that, The face capture pose acquisition module includes: The user image acquisition submodule is used to acquire user images captured by the camera device; The pose recognition submodule is used to recognize the user image to obtain the face capture pose parameters.

10. The virtual character drive control device according to claim 6, characterized in that, The device further includes: The model deployment module is used to deploy a pre-set image processing model in the cloud; the pre-set image processing model is used to extract features from the image of the virtual character to obtain image feature information.

11. 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 implements the steps of the driving control method for the virtual character as described in any one of claims 1 to 5.

12. 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 driving control method for the virtual character according to any one of claims 1 to 5.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the driving control method for the virtual character as described in any one of claims 1 to 5.

Images