Research map / 3D vision / Depth and stereo
UASNet: Uncertainty Adaptive Sampling Network for Deep Stereo Matching
Yamin Mao, Zhihua Liu, Weiming Li, Yuchao Dai, Qiang Wang, Yun-Tae Kim, Hong-Seok Lee
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 fixed offset with URP range prediction (ablation) | Cas2 · SceneFlow | EPE: 0.649 -> 0.623 | Improved |
| replace fixed offset with URP range prediction (ablation) | Cas2 · KITTI 2015 | All error: 2.0 -> 1.87 | Improved |
| replace variance-based range with URP (ablation) | Cas2+variances · SceneFlow | EPE: 0.645 -> 0.623 | Improved |
| add UDS sampling to URP (ablation) | Cas2+URP · SceneFlow | EPE: 0.623 -> 0.619 | Improved |
| add URP range prediction (ablation) | Cas3 · SceneFlow | EPE: 0.581 -> 0.554 | Improved |
| add UDS sampling to URP (ablation) | Cas3+URP · SceneFlow | EPE: 0.554 -> 0.527 | Improved |
| add URP and UDS (ablation) | Cas3 · KITTI 2015 | All error: 1.75 -> 1.66 | Improved |
| add URP range prediction (ablation) | Cas3 · SceneFlow | covering ratio: 97.36 -> 98.71 | Improved |
| replace variance-based range with URP (ablation) | Cas2 · SceneFlow | covering ratio: 97.72 -> 99.39 | Improved |
| replace fixed offset with URP range prediction (ablation) | Cas2 · SceneFlow | covering ratio: 99.04 -> 99.39 | No clear effect |
| add URP range prediction (ablation) | DeepPruner* · SceneFlow | EPE: 0.996 -> 0.934 | Improved |
| add UDS sampling to URP (ablation) | DeepPruner*+URP · SceneFlow | EPE: decreases EPE error by 9.5% | Improved |
Closest papers by meaning
- Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness (CVPR 2020 · similarity 0.90)
- CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching (CVPR 2021 · similarity 0.89)
- Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching (TPAMI 2023 · similarity 0.88)
- On the confidence of stereo matching in a deep-learning era: a quantitative evaluation (TPAMI 2021 · similarity 0.88)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · similarity 0.87)
- Modeling Stereo-Confidence out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep (AAAI 2024 · similarity 0.86)
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.
