Research map / 3D vision / Human pose estimation
RAM: Recover Any 3D Human Motion in-the-Wild
Sen Jia, Ning Zhu, Jinqin Zhong, Jiale Zhou, Huaping Zhang, Jenq-Neng Hwang, Lei Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use full RAM motion-aware tracking instead of SAM2-only tracking (ablation) | RAM · TrackID3x3 (Outdoor) | TI-HOTA: 38.60 -> 66.68 | Improved |
| use full RAM motion-aware tracking instead of SAM2-only tracking (ablation) | RAM · TrackID3x3 (Indoor) | TI-HOTA: 54.23 -> 75.07 | Improved |
| RAM zero-shot vs CoMotion on identity switches | RAM · PoseTrack18 | ID switches: 344 -> 15 | Improved |
| RAM vs 4DHumans (reproduced) on MOTA | RAM · PoseTrack18 | MOTA: 61.8 -> 57.7 | Hurt |
| RAM vs CoMotion on speed | RAM · PoseTrack21 | FPS: 5.68 -> 10.32 | Improved |
| RAM vs CoMotion on 3D error | RAM · 3DPW | MPJPE: 60.0 -> 53.0 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CoMotion — CoMotion: Concurrent Multi-person 3D Motion (ICLR 2025) · better on 9 of 9 shared results
- CLIFF — CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation (ECCV 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- HumanMM: Global Human Motion Recovery from Multi-shot Videos (CVPR 2025 · similarity 0.90)
- Decoupling Human and Camera Motion From Videos in the Wild (CVPR 2023 · similarity 0.89)
- Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos (CVPR 2026 · similarity 0.88)
- EIHMR: Collaborative Human-Camera Estimation for Global Human Mesh Recovery (NeurIPS 2026 · similarity 0.88)
- Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining (CVPR 2026 · similarity 0.87)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.87)
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.
