Research map / 3D vision / Depth and stereo
Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 jointly trained flow pairs to stereo-only training (ablation) | Ours stereo model · KITTI 2015 stereo set | Abs Rel: 0.078 -> 0.0653 | Helped |
| add 2-warp consistency to joint flow-and-stereo training (ablation) | Ours (flow + stereo) · KITTI 2015 stereo set | Abs Rel: 0.0653 -> 0.0620 | Helped |
| add jointly trained flow pairs to stereo-only training (ablation) | Ours stereo model · KITTI raw Eigen split | Abs Rel: 0.090 -> 0.094 | Hurt |
| add 2-warp consistency to joint flow-and-stereo training (ablation) | Ours (flow + stereo) · KITTI raw Eigen split | Abs Rel: 0.094 -> 0.088 | Helped |
| add stereo pairs and shared stereo-flow training (ablation) | Ours flow model · KITTI 2012 | EPE-all: 4.29 -> 2.64 | Helped |
| add 2-warp consistency to joint flow-and-stereo training (ablation) | Ours (flow + stereo) · KITTI 2012 | EPE-all: 2.64 -> 2.56 | Helped |
| add stereo pairs and shared stereo-flow training (ablation) | Ours flow model · KITTI 2015 | EPE-all: 9.70 -> 7.47 | Helped |
| add 2-warp consistency to joint flow-and-stereo training (ablation) | Ours (flow + stereo) · KITTI 2015 | EPE-all: 7.47 -> 7.021 | Helped |
| use separate untied weights instead of shared weights (ablation) | Ours full-2 · KITTI 2015 | EPE-all: 7.044 -> 8.78 | Hurt |
| replace the Monodepth backbone with PWC-Net (ablation) | Ours · KITTI raw Eigen split | Abs Rel: 0.088 -> 0.058 | Helped |
| replace the Monodepth backbone with PWC-Net (ablation) | Ours · KITTI 2015 | EPE-all: 7.04 -> 6.66 | Helped |
| choose among the three investigated 2-warp operation directions (ablation) | Ours full model · KITTI 2015 | EPE-all: 7.021; 7.044; 7.134 | No clear effect |
Closest papers by meaning
- Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion (CVPR 2021 · similarity 0.93)
- Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching (CVPR 2020 · similarity 0.92)
- GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose (CVPR 2018 · similarity 0.89)
- Rethinking Optical Flow From Geometric Matching Consistent Perspective (CVPR 2023 · similarity 0.88)
- UFM: A Simple Path towards Unified Dense Correspondence with Flow (NeurIPS 2025 · similarity 0.88)
- Rectification-specific Supervision and Constrained Estimator for Online Stereo Rectification (CVPR 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.