Animation processing method and apparatus, computer storage medium, and electronic device

1. An animation processing method performed by an electronic device, the method comprising:

obtaining a terrain feature in a graphical user interface at a current moment, the graphical user interface including a virtual character, and obtaining state information and task information that correspond to the virtual character in an animation segment at the current moment;

inputting the terrain feature, the state information, and the task information to an animation processing model, and performing feature extraction on the terrain feature, the state information, and the task information using the animation processing model, to obtain joint action information corresponding to the virtual character at a next moment;

determining a joint torque according to the joint action information; and

obtaining gesture adjustment information corresponding to the virtual character from the current moment to the next moment based on the joint torque, and updating the animation segment according to the gesture adjustment information to render the updated animated segment in the graphical user interface.

2. The animation processing method according to claim 1 , further comprising:

when the current moment is an initial moment of the animation segment, determining the state information according to gesture information of the virtual character at the initial moment of the animation segment; and

when the current moment is a non-initial moment of the animation segment, determining the state information according to joint action information corresponding to the virtual character at a previous moment.

3. The animation processing method according to claim 2 , further comprising:

obtaining gesture adjustment information corresponding to the virtual character at a plurality of moments based on the animation segment; and

determining a target action sequence according to the gesture adjustment information at the plurality of moments.

4. The animation processing method according to claim 1 , wherein the terrain feature is a feature of a self-defined terrain or a feature of a real-life terrain;

the state information comprises a gesture, a speed, and a phase of each joint of the virtual character; and

the task information comprises a target speed direction or a target point coordinate corresponding to the virtual character.

5. The animation processing method according to claim 1 , wherein the animation processing model comprises a first control network and a second control network; and

the performing feature extraction on the terrain feature, the state information, and the task information using the animation processing model, to obtain joint action information corresponding to the virtual character at a next moment comprises:

inputting the terrain feature, the state information, and the task information to the first control network, and performing feature extraction on the terrain feature, the state information, and the task information using the first control network, to obtain target state information corresponding to a key joint, the key joint being a joint corresponding to the terrain feature, and the state information and the task information of the virtual character; and

inputting the state information and the target state information to the second control network, and performing feature extraction on the state information and the target state information using the second control network, to obtain the joint action information.

6. The animation processing method according to claim 5 , wherein the first control network comprises a convolution unit, a first fully connected layer, a second fully connected layer, and a third fully connected layer; and

the performing feature extraction on the terrain feature, the state information, and the task information using the first control network, to obtain target state information corresponding to a key joint comprises:

performing feature extraction on the terrain feature using the convolution unit, to obtain first feature information corresponding to a terrain;

performing feature combination on the first feature information using the first fully connected layer, to obtain second feature information;

performing feature combination on the second feature information, the state information, and the task information using the second fully connected layer, to obtain third feature information; and

performing feature combination on the third feature information using the third fully connected layer, to obtain the target state information.

7. The animation processing method according to claim 5 , wherein the second control network comprises a fourth fully connected layer and a fifth fully connected layer; and

the performing feature extraction on the state information and the target state information using the second control network, to obtain the joint action information comprises:

performing feature combination on the state information and the target state information using the fourth fully connected layer, to obtain fourth feature information; and

performing feature combination on the fourth feature information using the fifth fully connected layer, to obtain the joint action information.

8. The animation processing method according to claim 1 , wherein the determining a joint torque according to the joint action information comprises:

determining a current position and a target position of a joint according to the joint action information;

determining a current speed and a current acceleration of the joint according to the current position, and a target speed of the joint according to the target position, respectively;

determining a first position and a first speed that correspond to the joint after a next control period according to the current speed and the current acceleration; and

calculating the joint torque according to a proportional coefficient, a derivative gain coefficient, the current position, the target position, the target speed, the first position, and the first speed.

9. The animation processing method according to claim 1 , wherein the obtaining gesture adjustment information corresponding to the virtual character at the current moment based on the joint torque comprises:

inputting the joint torque to a physical engine, applying the joint torque to a corresponding joint using the physical engine, and rendering the corresponding joint, to generate the gesture adjustment information.

10. An electronic device, comprising:

one or more processors; and

memory, configured to store one or more computer programs, the one or more computer programs, when executed by the one or more processors, causing the electronic device to perform an animation processing method including:

obtaining a terrain feature in a graphical user interface at a current moment, the graphical user interface including a virtual character, and obtaining state information and task information that correspond to the virtual character in an animation segment at the current moment;

inputting the terrain feature, the state information, and the task information to an animation processing model, and performing feature extraction on the terrain feature, the state information, and the task information using the animation processing model, to obtain joint action information corresponding to the virtual character at a next moment;

determining a joint torque according to the joint action information; and

obtaining gesture adjustment information corresponding to the virtual character from the current moment to the next moment based on the joint torque, and updating the animation segment according to the gesture adjustment information to render the updated animated segment in the graphical user interface.

11. The electronic device according to claim 10 , wherein the animation processing method further include:

when the current moment is an initial moment of the animation segment, determining the state information according to gesture information of the virtual character at the initial moment of the animation segment; and

when the current moment is a non-initial moment of the animation segment, determining the state information according to joint action information corresponding to the virtual character at a previous moment.

12. The electronic device according to claim 11 , wherein the animation processing method further include:

obtaining gesture adjustment information corresponding to the virtual character at a plurality of moments based on the animation segment; and

determining a target action sequence according to the gesture adjustment information at the plurality of moments.

13. The electronic device according to claim 10 , wherein the terrain feature is a feature of a self-defined terrain or a feature of a real-life terrain;

the state information comprises a gesture, a speed, and a phase of each joint of the virtual character; and

the task information comprises a target speed direction or a target point coordinate corresponding to the virtual character.

14. The electronic device according to claim 10 , wherein the animation processing model comprises a first control network and a second control network; and

the performing feature extraction on the terrain feature, the state information, and the task information using the animation processing model, to obtain joint action information corresponding to the virtual character at a next moment comprises:

inputting the terrain feature, the state information, and the task information to the first control network, and performing feature extraction on the terrain feature, the state information, and the task information using the first control network, to obtain target state information corresponding to a key joint, the key joint being a joint corresponding to the terrain feature, and the state information and the task information of the virtual character; and

inputting the state information and the target state information to the second control network, and performing feature extraction on the state information and the target state information using the second control network, to obtain the joint action information.

15. The electronic device according to claim 10 , wherein the determining a joint torque according to the joint action information comprises:

determining a current position and a target position of a joint according to the joint action information;

determining a current speed and a current acceleration of the joint according to the current position, and a target speed of the joint according to the target position, respectively;

determining a first position and a first speed that correspond to the joint after a next control period according to the current speed and the current acceleration; and

calculating the joint torque according to a proportional coefficient, a derivative gain coefficient, the current position, the target position, the target speed, the first position, and the first speed.

16. The electronic device according to claim 10 , wherein the obtaining gesture adjustment information corresponding to the virtual character at the current moment based on the joint torque comprises:

inputting the joint torque to a physical engine, applying the joint torque to a corresponding joint using the physical engine, and rendering the corresponding joint, to generate the gesture adjustment information.

17. A non-transitory computer-readable storage medium, storing one or more computer programs, the one or more computer programs, when executed by one or more processors of an electronic device, causing the electronic device to perform an animation processing method including:

obtaining a terrain feature in a graphical user interface at a current moment, the graphical user interface including a virtual character, and obtaining state information and task information that correspond to the virtual character in an animation segment at the current moment;

inputting the terrain feature, the state information, and the task information to an animation processing model, and performing feature extraction on the terrain feature, the state information, and the task information using the animation processing model, to obtain joint action information corresponding to the virtual character at a next moment;

determining a joint torque according to the joint action information; and

obtaining gesture adjustment information corresponding to the virtual character from the current moment to the next moment based on the joint torque, and updating the animation segment according to the gesture adjustment information to render the updated animated segment in the graphical user interface.

18. The non-transitory computer-readable storage medium according to claim 17 , wherein the animation processing method further include:

when the current moment is an initial moment of the animation segment, determining the state information according to gesture information of the virtual character at the initial moment of the animation segment; and

when the current moment is a non-initial moment of the animation segment, determining the state information according to joint action information corresponding to the virtual character at a previous moment.

19. The non-transitory computer-readable storage medium according to claim 18 , wherein the animation processing method further include:

obtaining gesture adjustment information corresponding to the virtual character at a plurality of moments based on the animation segment; and

determining a target action sequence according to the gesture adjustment information at the plurality of moments.

20. The non-transitory computer-readable storage medium according to claim 17 , wherein the obtaining gesture adjustment information corresponding to the virtual character at the current moment based on the joint torque comprises:

inputting the joint torque to a physical engine, applying the joint torque to a corresponding joint using the physical engine, and rendering the corresponding joint, to generate the gesture adjustment information.