AI RESEARCH
B\'ezier Degradation Modeling for LiDAR-based Human Motion Capture
arXiv CS.CV
•
ArXi:2605.19620v1 Announce Type: new LiDAR-based 3D human motion capture has broad applications in fields such as autonomous driving and robotics, where accurate motion reconstruction is crucial. However, existing methods often struggle with unstable inputs and severe occlusions, leading to jittery or even failed pose predictions. To address these challenges, we propose BMLiCap, a coarse-to-fine framework that models motion using temporally compressible B\'ezier curves.