Skeleton animation posture matching method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a skeletal animation posture matching method and device, electronic equipment and a storage medium. The skeletal animation posture matching method comprises the steps: receiving any frame of data in skeletal animation; and obtaining candidate matching nodes corresponding to the any frame of data from a pre-obtained motion graph model, wherein the motion graph model comprises a plurality of nodes connected through directed edges according to an excessive situation, and the plurality of nodes represent a plurality of motion frames in the motion graph sequence respectively; obtaining the similarity between any frame of data and each node in the candidate matching nodes; and based on the similarity between any frame of data and each node, obtaining a matching node of any frame of data from the candidate matching nodes. According to the embodiment of the invention, the accuracy and matching efficiency of the posture matched by the skeletal animationcan be ensured, and the smooth transition of the posture of each frame of data in the skeletal animation is improved.

Description

technical field [0001] The invention relates to the technical field of computer graphics processing, in particular to a pose matching method, device, electronic device and storage medium for skeletal animation. Background technique [0002] Converting the 3D key points of the bones into the rotation matrices of the corresponding joints is the key link to drive the motion of the virtual human. At present, the inverse kinematics algorithm is generally used to impose specific constraints on each joint, and then iteratively solve it to obtain the rotation information corresponding to each joint. However, different joints need to impose different constraints, and different algorithms have different time consumption and solution goals. It is also different, which leads to the situation that some movements may have no solution. Due to the inaccurate grasp of constraints, because the human body has a complex composition, the movements of different parts may involve the linkage effec...

AI Technical Summary

Problems solved by technology

At present, the inverse kinematics algorithm is generally used to impose specific constraints on each joint, and then iteratively solve the problem to obtain the corresponding rotation information of each joint. However, different joints need to impose different constraints, and different algorithms have different time consumption and solution goals. It is also different, which leads to the situation that some sports may have no solution. Due to the inaccurate grasp of the constraints and the complex composition of the human body, the movements of different parts may involve the linkage effect of other joints. Therefore, the matching accuracy is relatively low. Difference

The method of deep learning reconstructs the rotation data of future frames according to the 3D key points and historical frame information through the study of a large amount of data, but the amount of data required is large enough, and the phenomenon of cumulative errors is prone to occur, which leads to the prediction of subsequent frames worse and worse

Images