AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching

Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Zhe Wang, Jianping Shi

CVPR 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 79 citations (OpenAlex)

Check 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 changedWhereMeasuredEffect
Add progressive color transfer (ablation)Ada-PSMNet · KITTI 2015D1-error (%): 12.1 -> 5.4Improved
Add progressive color transfer (ablation)Ada-PSMNet · DrivingStereoD1-error (%): 20.9 -> 7.4Improved
Add cost normalization (ablation)Ada-PSMNet with progressive color transfer · KITTI 2015D1-error (%): 5.4 -> 4.7Improved
Add cost normalization (ablation)Ada-PSMNet with progressive color transfer · DrivingStereoD1-error (%): 7.4 -> 6.4Improved
Add self-supervised occlusion-aware reconstruction (ablation)Ada-PSMNet with color transfer and cost normalization · KITTI 2015D1-error (%): 4.7 -> 3.5Improved
Add self-supervised occlusion-aware reconstruction (ablation)Ada-PSMNet with color transfer and cost normalization · DrivingStereoD1-error (%): 6.4 -> 5.1Improved
Replace general normalization with cost normalization (ablation)PSMNet · KITTID1-error (%): 9.5 -> 9.1Improved
Replace general normalization with cost normalization (ablation)PSMNet · DrivingStereoD1-error (%): 17.2 -> 16.7Improved
Replace Reinhard-style color transfer with progressive color transfer (ablation)PSMNet · KITTID1-error (%): 6.2 -> 5.4Improved
Replace Reinhard-style color transfer with progressive color transfer (ablation)PSMNet · DrivingStereoD1-error (%): 8.3 -> 7.4Improved
Add patch localization, rotation prediction, or flip prediction instead of occlusion-aware reconstruction (ablation)PSMNet with color transfer and cost normalization · KITTI training setD1-error (%): 4.7 -> 6.5; 4.7 -> 6.1; 4.7 -> 6.0Hurt
Adapt the source-trained stereo model using AdaStereo's multi-level alignmentPSMNet · Middlebury training setD1-error (%): 25.1 -> 8.4Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy