Jul 2026
Absolute-scale 3D human pose estimation from monocular videos via relative depth priors and multi-frame fusion
A lightweight, annotation-efficient solution for absolute-scale 3D human pose estimation using only relative depth priors and sparse supervision that supports applications in smart sports, human–computer interaction, and virtual reality, broadening the deployment scope of monocular 3D pose systems.
Huagang He, Yinghao Li, Beiyang Liu et al.
· The Visual Computer · 0 citations