Research map / 3D vision / Depth and stereo
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
Haiwen Feng, Junyi Zhang, Qianqian Wang, Yufei Ye, Pengcheng Yu, Michael J. Black, Trevor Darrell, Angjoo Kanazawa
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 St4RTrack world-frame tracking instead of SpaTracker | SpaTracker · WorldTrack Panoptic Studio (all points) | APD3D: 62.59 -> 69.67 | Improved |
| use St4RTrack instead of MonST3R | MonST3R · WorldTrack Point Odyssey (all points) | APD3D: 33.47 -> 67.95 | Improved |
| use St4RTrack instead of MonST3R | MonST3R · WorldTrack ADT (all points) | APD3D: 74.35 -> 76.01 | Improved |
| use St4RTrack instead of SpaTracker+MonST3R combination | SpaTracker+MonST3R · WorldTrack Dynamic Replica (all points) | APD3D: 55.49 -> 73.74 | Improved |
| use St4RTrack instead of MonST3R with global alignment | MonST3R+GA · Point Odyssey (world recon) | EPE: 0.2629 -> 0.2406 | Improved |
| use St4RTrack instead of MonST3R with global alignment | MonST3R+GA · TUM-Dynamics (world recon) | APD: 63.87 -> 83.42 | Improved |
| use St4RTrack instead of DUSt3R feed-forward | DUSt3R · TUM-Dynamics (world recon) | EPE: 0.2891 -> 0.1854 | Improved |
| add test-time adaptation with reprojection losses (ablation) | St4RTrack · WorldTrack dynamic points | APD3D | Improved |
| add test-time adaptation (reconstruction branch frozen) (ablation) | St4RTrack · Point Odyssey and TUM-Dynamics reconstruction | EPE/APD | No clear effect |
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.
- MonST3R — MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025) · better on 8 of 8 shared results
- DUSt3R — DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024) · better on 4 of 4 shared results
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
- Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels (ECCV 2026 · similarity 0.90)
- Efficiently Reconstructing Dynamic Scenes One D4RT at a Time (CVPR 2026 · similarity 0.90)
- TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking (NeurIPS 2026 · similarity 0.88)
- Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos (CVPR 2025 · similarity 0.88)
- Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video (NeurIPS 2025 · similarity 0.88)
- TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels (NeurIPS 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.
