Open access
Jul 2026
OAHPE: occlusion-aware hybrid routing for efficient and robust 3D human pose estimation in mixed-occlusion videos.
The OAHPE model is proposed to address the dual challenges of high uncertainty in occluded frames and high redundancy in visible frames during 3D human pose estimation from video, and attains superior performance with substantially lower parameter and memory costs.
Guoying Sun, Ya Huang, Kaisen Li et al.
· Scientific Reports · 0 citations