Research map / 3D vision / Depth and stereo
Deep Rigid Instance Scene Flow
Wei-Chiu Ma, Shenlong Wang, Rui Hu, Yuwen Xiong, Raquel Urtasun
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 |
|---|---|---|---|
| model each instance with rigid motion and jointly optimize geometry-based energy terms | KITTI scene flow estimation · KITTI scene flow test | Scene Flow all: 8.08 -> 6.31 | Improved |
| use only photometric energy for background motion (ablation) | DRISF background · KITTI scene flow val, background | SF outliers (%): 5.21 -> 4.30 | Improved |
| add flow and rigid energies to photometric energy (ablation) | DRISF background · KITTI scene flow val, background | SF outliers (%): 4.30 -> 5.21 | Hurt |
| add flow and rigid energies to photometric energy (ablation) | DRISF foreground · KITTI scene flow val, foreground | SF outliers (%): 9.00 -> 8.39 | Improved |
| add flow and rigid energies to photometric energy (ablation) | DRISF foreground · KITTI scene flow val, foreground | Fl outliers (%): 7.57 -> 6.73 | Improved |
| replace predicted disparity 1 and optical flow inputs with ground truth (ablation) | DRISF · KITTI scene flow val | scene flow error rate: 8% | Improved |
| replace predicted optical flow with ground truth (ablation) | DRISF · KITTI scene flow val | scene flow error rate: 21% | Improved |
| replace predicted instance segmentation with ground truth (ablation) | DRISF · KITTI scene flow val | scene flow error rate | No clear effect |
| pad out-of-image warping samples with the nearest boundary feature instead of zero (ablation) | PWC-Net flow module in DRISF · KITTI scene flow | flow estimation performance | Improved |
| use the structured rigid-motion pipeline rather than unstructured flow and stereo outputs | DRISF · KITTI scene flow val | SF-all: 50.8 -> 4.84 | Improved |
Closest papers by meaning
- Weakly Supervised Learning of Rigid 3D Scene Flow (CVPR 2021 · similarity 0.92)
- Just Go With the Flow: Self-Supervised Scene Flow Estimation (CVPR 2020 · similarity 0.90)
- Exploiting Semantic Information and Deep Matching for Optical Flow (ECCV 2016 · similarity 0.89)
- ICP-Flow: LiDAR Scene Flow Estimation with ICP (CVPR 2024 · similarity 0.87)
- Zero-Shot Monocular Scene Flow Estimation in the Wild (CVPR 2025 · similarity 0.86)
- VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow (CVPR 2025 · 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.
