Research map / Label-efficient and robust learning / Recognition and long-tail
CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation
Read the paperCheck 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 |
|---|---|---|---|
| Coalesce four conventional matching costs with bidirectional confidence features using a random forest | CBMV · ETH3D two-view benchmark Out-Noc | bad 1.0: 10.08% -> 5.35% | Helped |
| Use CBMV instead of MC-CNN-acrt | stereo disparity estimation · Middlebury 2014 test set | avgerror all: 17.9 -> 14.4 | Helped |
| Use CBMV instead of MC-CNN-acrt | stereo disparity estimation · Middlebury 2014 test set | bad-2.0 nonocc: 8.08% -> 11.1% | Hurt |
| Train the classifier on Middlebury 2014 and transfer it to KITTI 2012 rather than training on KITTI 2012 | CBMV · KITTI 2012 Out-Noc | relative increase in error rate: 0% | No clear effect |
| Train the classifier on Middlebury 2014 and transfer it to KITTI 2015 rather than training on KITTI 2015 | CBMV · KITTI 2015 Out-All | relative increase in error rate: -2.09% | No clear effect |
| Train the classifier on Middlebury 2014 and transfer it to KITTI 2012 | CBMV · KITTI 2015 Out-All | relative increase in error rate: -0.41% | Helped |
| Train the classifier on KITTI 2015 and transfer it to Middlebury 2014 | CBMV · Middlebury 2014 bad 2.0 | relative increase in error rate: 7.69% | Hurt |
| Train the classifier on KITTI 2012 and transfer it to Middlebury 2014 | CBMV · Middlebury 2014 bad 2.0 | relative increase in error rate: 7.00% | Hurt |
| Use CBMV instead of MC-CNN-fst when transferring from KITTI 2015 to Middlebury 2014 | stereo disparity estimation · Middlebury 2014 bad 2.0 | relative increase in error rate: 41.62% -> 7.69% | Helped |
| Use CBMV instead of MC-CNN-fst when transferring from KITTI 2012 to Middlebury 2014 | stereo disparity estimation · Middlebury 2014 bad 2.0 | relative increase in error rate: 33.58% -> 7.00% | Helped |
Closest papers by meaning
- 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 0.90)
- Modeling Stereo-Confidence out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep (AAAI 2024 · similarity 0.88)
- Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation (CVPR 2023 · similarity 0.88)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · similarity 0.88)
- Hierarchical Object-Aware Dual-Level Contrastive Learning for Domain Generalized Stereo Matching (NeurIPS 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.