Research map / Label-efficient and robust learning / Domain adaptation and generalization
AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach
Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Yuexin Ma, Zhe Wang, Jianping Shi
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 progressive color transfer (ablation) | Ada-PSMNet · KITTI 2015 train | D1-error (%): 12.1 -> 5.4 | Improved |
| add cost normalization (ablation) | Ada-PSMNet · KITTI 2015 train | D1-error (%): 12.1 -> 9.1 | Improved |
| add self-supervised occlusion-aware reconstruction (ablation) | Ada-PSMNet · KITTI 2015 train | D1-error (%): 4.7 -> 3.5 | Improved |
| use progressive update (gamma 0.95) instead of none (gamma 1) (ablation) | progressive color transfer · KITTI train | D1-error (%): 6.2 -> 5.4 | Improved |
| combine channel and pixel normalization (ablation) | cost normalization · KITTI train | D1-error (%): 12.1 -> 9.1 | Improved |
| replace general normalization layers with cost norm (ablation) | PSMNet · KITTI train | D1-error (%): 10.7 -> 9.1 | Improved |
| use progressive color transfer instead of Reinhard color transfer (ablation) | PSMNet · KITTI train | D1-error (%): 6.2 -> 5.4 | Improved |
| use progressive color transfer instead of GAN-based transfer (ablation) | PSMNet · KITTI train | D1-error (%): 8.0 -> 5.4 | Improved |
| add high-level auxiliary tasks (rotation, flip, patch localization) (ablation) | PSMNet baseline · KITTI train | D1-error (%): 12.1 -> 14.6 | Hurt |
| add source-domain occlusion mask loss (ablation) | Ada-PSMNet · DrivingStereo train | D1-error (%): 5.4 -> 5.1 | Improved |
| add disparity smoothness loss (ablation) | Ada-PSMNet · DrivingStereo train | D1-error (%): 5.2 -> 5.1 | Improved |
| use fewer target-domain training pairs (1/5) (ablation) | Ada-PSMNet · DrivingStereo train | D1-error (%): 5.4 -> 5.1 | No clear effect |
Closest papers by meaning
- AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching (CVPR 2021 · similarity 0.99)
- Domain-invariant Stereo Matching Networks (ECCV 2020 · similarity 0.92)
- Learning Representations from Foundation Models for Domain Generalized Stereo Matching (ECCV 2024 · similarity 0.91)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.90)
- Hierarchical Object-Aware Dual-Level Contrastive Learning for Domain Generalized Stereo Matching (NeurIPS 2024 · similarity 0.90)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · similarity 0.89)
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.
