Research map / 3D vision / Human pose estimation
TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments
Yu Sun, Qian Bao, Wu Liu, Tao Mei, Michael J. Black
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 |
|---|---|---|---|
| Add the memory unit for persistent tracking under occlusion (ablation) | TRACE · MuPoTS | MOTA: decreases 6.5% | Improved |
| Add the memory unit for persistent tracking under occlusion (ablation) | TRACE · Dyna3DPW | MOTA: decreases 11.1% | Improved |
| Add the memory unit for persistent tracking under occlusion (ablation) | TRACE · MuPoTS | IDF1: decreases 12.0% | Improved |
| Add the memory unit for persistent tracking under occlusion (ablation) | TRACE · Dyna3DPW | IDF1: decreases 49.1% | Improved |
| Add the memory unit for persistent tracking under occlusion (ablation) | TRACE · MuPoTS | HOTA: decreases 8.0% | Improved |
| Add the memory unit for persistent tracking under occlusion (ablation) | TRACE · Dyna3DPW | HOTA: decreases 39.6% | Improved |
| Add the memory unit (ablation) | TRACE · MuPoTS/Dyna3DPW | ID switches: increase 31/94 without the memory unit | Improved |
| Use TFP without optical flow from the motion backbone (ablation) | 5DRL · 3DPW | PAMPJPE: outperforms BEV by 18.1% (38.4mm) | Improved |
| Add temporal motion features from the motion backbone (ablation) | 5DRL with TFP · 3DPW | PAMPJPE: reduces PAMPJPE by 1.6% (37.8mm) | Improved |
Later papers that compared with this method
9 later accepted papers report TRACE as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.
- ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolation (CVPR 2026 · better on 4 of 6 shared results)
- QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture (ICLR 2026 · better on 4 of 4 shared results)
- DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes (ECCV 2026 · better on 1 of 1 shared result)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · better on 3 of 4 shared results)
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · better on 3 of 3 shared results)
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR 2024 · better on 4 of 4 shared results)
- Generating Human Interaction Motions in Scenes with Text Control (ECCV 2024 · better on 4 of 4 shared results)
- Capturing Closely Interacted Two-Person Motions with Reaction Priors (CVPR 2024 · better on 3 of 3 shared results)
1 more not listed.
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
- TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos (CVPR 2026 · similarity 0.87)
- TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels (NeurIPS 2025 · similarity 0.86)
- CoMotion: Concurrent Multi-person 3D Motion (ICLR 2025 · similarity 0.85)
- BEDLAM2.0: Synthetic humans and cameras in motion (NeurIPS 2025 · similarity 0.85)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.85)
- Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions (NeurIPS 2024 · similarity 0.85)
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.
