Abstract: A drivable implicit three-dimensional human body representation method, which is used for performing dynamic reconstruction by means of optimizing a three-dimensional representation of a drivable model from an input multi-view video.

Abstract: Disclosed is a human motion capture method based on unsynchorized videos, which can effectively recover the 3D motion of a target person through multiple unsynchorized videos of the person. In order to utilize multiple unsynchorized videos, the present disclosure provides a video synchronization and motion reconstruction method. The present disclosure is implemented in the following steps: synchronizing multiple videos based on a 3D human pose; performing motion reconstruction based on synchronized videos, modeling the motion difference across different viewpoints by using the low-rank constraint to realize high-precision human motion capture from the plurality of unsynchorized videos. According to the present disclosure, more accurate motion capture is carried out by using multiple unsynchorized videos.