Research map / 3D vision / Human pose estimation
EIHMR: Collaborative Human-Camera Estimation for Global Human Mesh Recovery
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes EIHMR, a collaborative framework that jointly estimates camera ego-motion and human motion for global human mesh recovery from monocular moving-camera video, instead of the isolated two-stage pipeline.
Problem
Recovering global 3D human motion from monocular video with a moving camera, where camera ego-motion and body motion are entangled; the prevailing two-stage pipeline estimates camera and human motion separately, amplifying errors in world coordinates.
Approach
Replaces the isolated two-stage paradigm with collaborative human-camera estimation so that camera and human motion are estimated together, rather than letting errors from each stage compound in the world frame.
Closest papers by meaning
- Synergistic Global-space Camera and Human Reconstruction from Videos (CVPR 2024 · similarity 0.91)
- HumanMM: Global Human Motion Recovery from Multi-shot Videos (CVPR 2025 · similarity 0.89)
- WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion (CVPR 2024 · similarity 0.88)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.88)
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.88)
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.