Research map / 3D vision / Depth and stereo
Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching
Junpeng Jing, Jiankun Li, Pengfei Xiong, Jiangyu Liu, Shuaicheng Liu, Yichen Guo, Xin Deng, Mai Xu, Lai Jiang, Leonid Sigal
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 uncertainty estimation and content-aware warping instead of bilinear warping (ablation) | Lite-CREStereo++ · Middlebury | bad 2.0: 14.79 -> 11.86 | Improved |
| add uncertainty estimation on top of content-aware warping (ablation) | Lite-CREStereo++ · KITTI2015 | D1-all: 2.47 -> 2.36 | Improved |
| content-aware learnable warping without uncertainty vs bilinear (ablation) | Lite-CREStereo++ · Middlebury | bad 2.0: 14.79 -> 12.96 | Improved |
| use variance-based uncertainty instead of error-based map (ablation) | Lite-CREStereo++ · Middlebury | bad 2.0: 12.40 -> 11.86 | Improved |
| sigmoid instead of tanh in variance uncertainty (ablation) | Lite-CREStereo++ · Middlebury | bad 2.0: 11.98 -> 11.86 | Improved |
| GRU kernels 1x5 + 1x15 instead of 3x3 (ablation) | Lite-CREStereo++ · Middlebury | bad 2.0: 14.21 -> 11.86; +8ms runtime | Improved |
| add a third 1x31 GRU kernel (ablation) | Lite-CREStereo++ · Middlebury | bad 2.0: 11.86 -> 11.98 | Hurt |
| CREStereo++ vs CREStereo in cross-domain generalization from Scene Flow | CREStereo · ETH3D | bad 1.0: 5.5 -> 4.4 | Improved |
| use UGAC in lightweight model with 0.6M parameters | Lite-CREStereo++ · KITTI 2012 online | 3-all: 1.89 -> 1.82 vs HITNet | Improved |
Closest papers by meaning
- Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching (TPAMI 2023 · similarity 0.89)
- Robust Synthetic-to-Real Transfer for Stereo Matching (CVPR 2024 · similarity 0.87)
- Consistency-aware Self-Training for Iterative-based Stereo Matching (CVPR 2025 · similarity 0.86)
- Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching (CVPR 2024 · similarity 0.86)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · similarity 0.86)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 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.
