Research map / 3D vision / Human pose estimation
DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes
Chunggi Lee, Seonwook Park, Wanhua Li, Umar Iqbal, Hanspeter Pfister
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 |
|---|---|---|---|
| single-stage DETRAM vs CoMotion | multi-person tracking · PoseTrack21 | MOTA: 67.6 -> 71.0 | Improved |
| DETRAM vs CoMotion speed | tracking · PoseTrack21 | FPS: 5.68 -> 10.87 | Improved |
| add user prompts at inference | DETRAM · PoseTrack21 | MOTA: 73.6 -> 75.7 | Improved |
| DETRAM vs CoMotion on BEDLAM identity switches | tracking · BEDLAM | ID switches: 885 -> 37 | Improved |
| DETRAM vs CoMotion on reconstruction | HMR · BEDLAM | PA-MPJPE: 24.50 -> 31.24 | Hurt |
| DETRAM vs CoMotion on 3DPW reconstruction | HMR · 3DPW | PA-MPJPE: 37.3 -> 38.3 | Mixed |
| add tracking queries (ablation) | DETRAM · PoseTrack21 | MOTA: 68.9 -> 73.6 | Improved |
| add memory bank (ablation) | DETRAM · PoseTrack21 | MOTA: 73.3 -> 73.6 | Improved |
| add memory bank (ablation) | DETRAM · BEDLAM | MPJPE: 47.33 -> 48.68 | Hurt |
| add memory bank (ablation) | DETRAM · BEDLAM | ID switches: 32 -> 37 | Hurt |
| use TMCA instead of direct propagation (ablation) | DETRAM · PoseTrack21 | MOTA: 71.7 -> 73.6 | Improved |
| add content-conditioned query modulation (ablation) | DETRAM · BEDLAM | ID switches: 305 -> 37 | 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 11 of 11 shared results
- TRACE — TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments (CVPR 2023) · 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
- MuCHeR: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking (ECCV 2026 · similarity 0.93)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · similarity 0.89)
- SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens (CVPR 2025 · similarity 0.87)
- AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation (CVPR 2024 · similarity 0.87)
- CoMotion: Concurrent Multi-person 3D Motion (ICLR 2025 · similarity 0.87)
- Reconstructing People, Places, and Cameras (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.
