US 12,236,513 B2
Virtual character posture adjustment
Qunfen Lin, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on Jan. 19, 2024, as Appl. No. 18/417,940.
Application 18/417,940 is a continuation of application No. 17/686,947, filed on Mar. 4, 2022, granted, now 11,928,765.
Application 17/686,947 is a continuation of application No. PCT/CN2020/123677, filed on Oct. 26, 2020.
Claims priority of application No. 202010059845.3 (CN), filed on Jan. 19, 2020.
Prior Publication US 2024/0153187 A1, May 9, 2024
Int. Cl. G06T 7/20 (2017.01); G06T 7/73 (2017.01); G06T 13/40 (2011.01); G06V 10/774 (2022.01); G06V 20/40 (2022.01)
CPC G06T 13/40 (2013.01) [G06T 7/20 (2013.01); G06T 7/74 (2017.01); G06V 10/7747 (2022.01); G06V 20/46 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 17 Claims
OG exemplary drawing
 
1. An information processing method, comprising:
obtaining a first key frame by processing circuitry of an information processing apparatus, the first key frame comprising initial posture data of a target virtual character, the initial posture data corresponding to an initial posture of the target virtual character, wherein the initial posture data of the target virtual character includes respective initial position data and initial rotation data of a second set of joints of the target virtual character, the second set of joints including at least one first joint of a first set of joints;
determining target posture data of the target virtual character by inputting the initial posture data and a target task to a policy network trained by reinforcement learning, the target task being set for the target virtual character to perform, an output of the policy network indicating the target posture data that corresponds to a target posture of the target virtual character, wherein the target posture data of the target virtual character includes respective target position data and target rotation data of the second set of joints of the target virtual character;
determining at least one force to be acted on the at least one first joint of the target virtual character according to the initial posture data, and the target posture data of the target virtual character; and
adjusting a posture of the target virtual character from the initial posture to the target posture by applying the at least one force on the at least one first joint to obtain a second key frame.