Research map / 3D vision / Depth and stereo
Beyond local reasoning for stereo confidence estimation with deep learning
Fabio Tosi, Matteo Poggi, Antonio Benincasa, Stefano Mattoccia
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 |
|---|---|---|---|
| add global ConfNet branch and cascaded fusion to CCNN | CCNN with AD-CENSUS · KITTI 2012 | AUC: 0.1207 -> 0.1174 | Improved |
| add global ConfNet branch and cascaded fusion to CCNN | CCNN with MC-CNN · KITTI 2012 | AUC: 0.0291 -> 0.0279 | Improved |
| add global ConfNet branch and cascaded fusion to CCNN | CCNN with SGM · KITTI 2012 | AUC: 0.0194 -> 0.0176 | Improved |
| add global ConfNet branch and cascaded fusion to CCNN | CCNN with SGM · KITTI 2015 | AUC: 0.0201 -> 0.0193 | Improved |
| add global ConfNet branch and cascaded fusion to CCNN | CCNN with SGM · Middlebury v3 (cross-validation) | AUC: 0.0794 -> 0.0703 | Improved |
| add global ConfNet branch and cascaded fusion to CCNN | CCNN with AD-CENSUS · Middlebury v3 (cross-validation) | AUC: 0.1131 -> 0.1099 | Improved |
| use global ConfNet alone instead of local CCNN | ConfNet with AD-CENSUS · KITTI 2012 | AUC: 0.1207 -> 0.1295 | Hurt |
| use global ConfNet alone instead of local CCNN | ConfNet with SGM · KITTI 2012 | AUC: 0.0194 -> 0.0199 | Hurt |
| replace local CCNN input with RGB-augmented early fusion EFN | CCNN with SGM · KITTI 2012 | AUC: 0.0194 -> 0.0229 | Hurt |
| add RGB image via late fusion LFN in place of CCNN | CCNN with MC-CNN · KITTI 2012 | AUC: 0.0291 -> 0.0294 | No clear effect |
| use LFN instead of CCNN as local network inside LGC-Net | LGC-Net with MC-CNN · KITTI 2012 | AUC: 0.0279 -> 0.0278 | No clear effect |
| use LFN instead of CCNN as local network inside LGC-Net | LGC-Net with SGM · Middlebury v3 (cross-validation) | AUC: 0.0703 -> 0.0709 | No clear effect |
Closest papers by meaning
- Learning to Predict Stereo Reliability Enforcing Local Consistency of Confidence Maps (CVPR 2017 · similarity 0.93)
- Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation (TPAMI 2022 · similarity 0.92)
- LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation (CVPR 2019 · similarity 0.92)
- Quantitative Evaluation of Confidence Measures in a Machine Learning World (ICCV 2017 · similarity 0.91)
- Modeling Stereo-Confidence out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep (AAAI 2024 · similarity 0.90)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 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.
