Research map / 3D vision / Depth and stereo
Robust Multi-Body Feature Tracker: A Segmentation-Free Approach
Pan Ji, Hongdong Li, Mathieu Salzmann, Yiran Zhong
Check 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 segmentation-free multi-body epipolar-subspace rigidity constraints | KLT-style feature tracking · Hopkins checkerboard | tracking errors: 34.69 -> 27.77; 30.86 -> 27.32; 29.69 -> 27.13; 30.16 -> 28.18; 31.16 -> 27.21 | Improved |
| add segmentation-free multi-body epipolar-subspace rigidity constraints | KLT-style feature tracking · Hopkins car-and-people | tracking errors: 21.71 -> 16.14; 29.31 -> 18.82; 36.32 -> 26.56; 46.49 -> 33.80; 56.92 -> 42.43 | Improved |
| add segmentation-free multi-body epipolar-subspace rigidity constraints | KLT-style feature tracking · MTPV | tracking errors: 3.07 -> 2.34; 8.84 -> 3.87; 11.17 -> 6.94; 11.26 -> 9.92; 12.34 -> 13.22 | Mixed |
| add segmentation-free multi-body epipolar-subspace rigidity constraints | KLT-style feature tracking · KITTI | tracking errors: 21.43 -> 14.18; 22.85 -> 16.70; 26.88 -> 17.70; 29.23 -> 20.33 | Improved |
| jointly track features and estimate subspace coefficients for frame-by-frame segmentation | Ours · 22 Hopkins sequences | motion segmentation error rate: 19.76 -> 8.97; 19.76 -> 9.35; 19.21 -> 9.33; 20.63 -> 9.89; 20.38 -> 11.26 | Improved |
Closest papers by meaning
- MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization (CVPR 2021 · similarity 0.87)
- SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation (AAAI 2026 · similarity 0.86)
- ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation (ICCV 2019 · similarity 0.86)
- Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering (TPAMI 2018 · similarity 0.86)
- TrackFlow: Multi-Object tracking with Normalizing Flows (ICCV 2023 · similarity 0.86)
- Multi-frame Motion Segmentation by Combining Two-Frame Results (IJCV 2022 · similarity 0.86)
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.
