Research map / Learning theory and algorithms / Prediction and decision losses
Learning to Predict Stereo Reliability Enforcing Local Consistency of Confidence Maps
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 |
|---|---|---|---|
| Apply the local-consistency CNN to Ensemble | Ensemble · KITTI 12 test (169 frames) | AUC: 0.214929 -> 0.127682 | Helped |
| Apply the local-consistency CNN to GCP | GCP · KITTI 12 test (169 frames) | AUC: 0.152764 -> 0.138078 | Helped |
| Apply the local-consistency CNN to Park | Park · KITTI 12 test (169 frames) | AUC: 0.144077 -> 0.132393 | Helped |
| Apply the local-consistency CNN to O1 | O1 · KITTI 12 test (169 frames) | AUC: 0.127645 -> 0.124695 | Helped |
| Apply the local-consistency CNN to CCNN | CCNN · KITTI 12 test (169 frames) | AUC: 0.123612 -> 0.121257 | Helped |
| Apply the local-consistency CNN to Ensemble | Ensemble · KITTI 15 | AUC: 0.186504 -> 0.109991 | Helped |
| Apply the local-consistency CNN to GCP | GCP · KITTI 15 | AUC: 0.139611 -> 0.124286 | Helped |
| Apply the local-consistency CNN to Park | Park · KITTI 15 | AUC: 0.131662 -> 0.117529 | Helped |
| Apply the local-consistency CNN to O1 | O1 · KITTI 15 | AUC: 0.108812 -> 0.105893 | Helped |
| Apply the local-consistency CNN to CCNN | CCNN · KITTI 15 | AUC: 0.105645 -> 0.103645 | Helped |
| Apply the local-consistency CNN to Ensemble | Ensemble · Middlebury 14 | AUC: 0.245227 -> 0.163656 | Helped |
| Apply the local-consistency CNN to GCP | GCP · Middlebury 14 | AUC: 0.109302 -> 0.098367 | Helped |
Closest papers by meaning
- Using Self-Contradiction to Learn Confidence Measures in Stereo Vision (CVPR 2016 · similarity 0.93)
- Modeling Stereo-Confidence out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep (AAAI 2024 · similarity 0.92)
- LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation (CVPR 2019 · similarity 0.90)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · similarity 0.89)
- Robust Synthetic-to-Real Transfer for Stereo Matching (CVPR 2024 · similarity 0.86)
- Neural Markov Random Field for Stereo Matching (CVPR 2024 · 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.