Video-based processing method and device, and readable medium

Abstract

The embodiment of the invention provides a video-based processing method and device, and a readable medium, so as to more accurately and naturally drive a virtual image to execute an action. The method comprises the following steps: acquiring a skeleton action segment, and dividing the skeleton action segment into skeleton action sub-segments; determining nodes by adopting the skeleton action sub-fragments, determining edges according to motion information among the skeleton action sub-fragments, and constructing a skeleton action connection graph; obtaining target information; according to the target information and skeleton action sub-fragments in a skeleton action connection graph, matching target sub-fragments and associated sub-fragments thereof; splicing the target sub-fragment and the associated sub-fragment, and combining the target information to form video data; and outputting the video data. The video with smooth transition of the action can be spliced, so that the action of the virtual user in the video data is natural and smooth, and the video of the virtual image execution action can be accurately and naturally generated.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a video-based processing method, a live broadcast processing method, a video generation method, a terminal device, and a machine-readable medium. Background technique [0002] Animation usually generates a corresponding animated video by drawing a picture of each frame. The animation picture is drawn based on the fixed plot of the animation. Correspondingly, the objects in the animation, such as characters and animals, are usually just a few fixed actions, which can form a dynamic effect. [0003] At present, there are avatars of some 3D characters that can perform singing and dancing performances. However, these avatars can only perform a few fixed actions, and the actions are relatively mechanical and rigid. Therefore, a technical problem that those skilled in the art need to solve is: how to Drive the avatar to perform actions more accurately and naturally. ...

AI Technical Summary

Problems solved by technology

[0003] At present, there are avatars of some 3D characters that can perform singing and dancing performances. However, these avatars can only perform a few fixed actions, and the actions are relatively mechanical and rigid. Therefore, a technical problem that those skilled in the art need to solve is: how to Drive the avatar to perform actions more accurately and naturally

Images