Research map / 3D vision / Depth and stereo
Fast Multi-Frame Stereo Scene Flow With Motion Segmentation
Tatsunori Taniai, Sudipta N. Sinha, Yoichi Sato
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 |
|---|---|---|---|
| Use FSF+MS instead of PRSM | KITTI 2015 scene flow benchmark · KITTI 2015 scene flow benchmark | SF-all error rate (%): 9.44 -> 15.54 | Hurt |
| Use FSF+MS instead of OSF | KITTI 2015 scene flow benchmark · KITTI 2015 scene flow benchmark | Time: 50 min -> 2.7 s | Improved |
| Add epipolar stereo refinement using temporally adjacent frames (ablation) | FSF+MS · KITTI training sequences, all pixels | D1-all error rate (%): 8.68 -> 6.51 | Improved |
| Add epipolar stereo refinement using temporally adjacent frames (ablation) | FSF+MS · KITTI training sequences, non-occluded pixels | D1-all error rate (%): 7.61 -> 6.06 | Improved |
Closest papers by meaning
- A Continuous Optimization Approach for Efficient and Accurate Scene Flow (ECCV 2016 · similarity 0.90)
- Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion (CVPR 2021 · similarity 0.89)
- Optical Flow in Mostly Rigid Scenes (CVPR 2017 · similarity 0.89)
- Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding (TPAMI 2019 · similarity 0.89)
- Dense Monocular Depth Estimation in Complex Dynamic Scenes (CVPR 2016 · similarity 0.88)
- Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos (CVPR 2025 · 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.
