Research map / 3D vision / Depth and stereo
Parameterized Cost Volume for Stereo Matching
Jiaxi Zeng, Chengtang Yao, Lidong Yu, Yuwei Wu, Yunde Jia
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 |
|---|---|---|---|
| replace single Gaussian fixed variance with multi-Gaussian adaptive variance (parameterized cost volume) (ablation) | RAFT-Stereo · SceneFlow, 4th iteration | EPE (px): 0.79 -> 0.72 | Improved |
| add adaptive variance to a single Gaussian (ablation) | RAFT-Stereo (SGFV) · SceneFlow, 4th iteration | EPE (px): 0.79 -> 0.82 | Hurt |
| use multi-Gaussian with fixed variance instead of single Gaussian (ablation) | RAFT-Stereo (SGFV) · SceneFlow, 4th iteration | 1px-error rate (%): 8.96 -> 8.93 | No clear effect |
| make multi-Gaussian variance adaptive (ablation) | MGFV · SceneFlow, 4th iteration | 1px-error rate (%): 8.93 -> 8.16 | Improved |
| add uncertainty-aware refinement module (ablation) | PCV · SceneFlow, 4th iteration | 1px-error rate (%): 8.16 -> 7.98 | Improved |
| add uncertainty-aware refinement module (ablation) | PCV · SceneFlow, 4th iteration | EPE (px): 0.72 -> 0.71 | Improved |
| use PCV instead of dynamic cost volume at same 4 iterations | RAFT-Stereo (T=4) · SceneFlow | EPE (px): 0.79 -> 0.71 | Improved |
| use PCV with 4 iterations instead of RAFT-Stereo with 32 iterations | RAFT-Stereo · SceneFlow | inference time (ms): 205 -> 41 | Improved |
| use PCV with 4 iterations instead of RAFT-Stereo with 4 iterations | RAFT-Stereo (T=4) · SceneFlow | FLOPS (G): 678.45 -> 798.23 | Hurt |
| use PCVNet instead of RAFT-Stereo on Booster | RAFT-Stereo · Booster | Bad 2 (%): 38.66 -> 27.41 | Improved |
| use PCVNet instead of CREStereo on KITTI 2015 for speed | CREStereo · KITTI 2015 | D1-all (%): 1.69 -> 1.93; 410 ms -> 56 ms | Mixed |
Closest papers by meaning
- A Memory- and Accuracy-Aware Gaussian Parameter-Based Stereo Matching Using Confidence Measure (TPAMI 2019 · similarity 0.90)
- Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching (CVPR 2020 · similarity 0.90)
- Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching (AAAI 2020 · similarity 0.90)
- CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching (CVPR 2021 · similarity 0.89)
- Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy (TPAMI 2019 · similarity 0.89)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · 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.
