Learning Variational Motion Prior for Video-based Motion Capture. (arXiv:2210.15134v1 [cs.CV])

Motion capture from a monocular video is fundamental and crucial for us
humans to naturally experience and interact with each other in Virtual Reality
(VR) and Augmented Reality (AR). However, existing methods still struggle with
challenging cases involving self-occlusion and complex poses due to the lack of
effective motion prior modeling. In this paper, we present a novel variational
motion prior (VMP) learning approach for video-based motion capture to resolve
the above issue. Instead of directly building the correspondence between …

arxiv motion capture prior video