New Method Aligns Monocular 3D Human Pose Estimates Across Multi-Camera Rigs
Researchers propose ray-lateral agreement to fuse monocular mesh estimates from calibrated multi-camera rigs, addressing geometric errors that place reconstructed bodies meters apart.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-19 05:00 · arXiv cs.CV
Trust the Ray, Not the Depth: Ray-Lateral Agreement for Multi-View 3D Human Pose Fusion