Research map / 3D vision / Depth and stereo
Dynamics Enhanced Multi-Camera Motion Segmentation From Unsynchronized Videos
Xikang Zhang, Bengisu Ozbay, Mario Sznaier, Octavia Camps
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 MDD dynamics feature to RSIM (ablation) | RSIM · Hopkins 155 (single camera) | overall mean clustering error (%): 1.01 -> 0.75 | Improved |
| use multi-camera McRSIM instead of RSIM | RSIM · Hopkins 155 (half rotated 45 deg and translated) | overall mean clustering error (%): 26.74 -> 1.30 | Improved |
| add MDD to McRSIM (ablation) | McRSIM · Hopkins 155 (half rotated 45 deg and translated) | overall mean clustering error (%): 1.30 -> 1.11 | Improved |
| add MDD to McRSIM (ablation) | McRSIM · Hopkins 155 (half delayed 4 frames) | overall mean clustering error (%): 1.71 -> 1.21 | Improved |
| add MDD to McRSIM (ablation) | McRSIM · Multiview Motion RSL 12 | overall mean clustering error (%): 0.02 -> 0.00 | No clear effect |
| add MDD to RSIM (ablation) | RSIM · Hopkins 155 (half delayed 4 frames) | overall mean clustering error (%): 13.57 -> 13.78 | Hurt |
| add MDD to LRR-H2 (ablation) | LRR-H2 · Hopkins 155 (half delayed 4 frames) | overall mean clustering error (%): 21.58 -> 22.10 | Hurt |
| add MDD to SSC (ablation) | SSC · Hopkins 155 (half rotated 45 deg and translated) | overall mean clustering error (%): 35.77 -> 34.72 | No clear effect |
| add MDD to RSIM (ablation) | RSIM · Hopkins 155 (5% grossly corrupted entries) | overall mean clustering error (%): 19.86 -> 19.64 | No clear effect |
| add MDD to RSIM-M (ablation) | RSIM-M · Hopkins 12 real sequences (missing data) | mean clustering error (%): 0.69 -> 0.61 | Improved |
| add per-camera clustering plus linear assignment on Stein means to RSIM-MDD | RSIM-MDD · Hopkins 155 (half rotated 45 deg and translated) | overall mean clustering error (%): 26.18 -> 2.15 | Improved |
| use McRSIM-M-MDD instead of RSIM-M-MDD with rotated second camera | McRSIM-M-MDD · Hopkins 12 real sequences (missing data, half rotated) | mean clustering error (%): 35.58 -> 7.15 | Improved |
Closest papers by meaning
- Multi-frame Motion Segmentation by Combining Two-Frame Results (IJCV 2022 · similarity 0.89)
- Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions (CVPR 2023 · similarity 0.88)
- Unsupervised Multi-Object Segmentation by Predicting Probable Motion Patterns (NeurIPS 2022 · similarity 0.88)
- MOVE: Motion-Guided Few-Shot Video Object Segmentation (ICCV 2025 · similarity 0.88)
- Learning to Segment Moving Objects (IJCV 2018 · similarity 0.87)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · 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.
