AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation

Qizhe Wei, Yingping Liang, Shao You, Ying Fu

ECCV 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
train on diffusion-rendered UW-Dataset instead of SceneFlowIGEV++ · FLSea-CanyonEPE: 5.41 -> 3.05Improved
train on UW-Dataset instead of StereoAdapter CG renderingIGEV++ · SquidEPE: 1.86 -> 1.80Improved
train on UW-Dataset instead of StereoAdapterIGEV++ · TartanAir (underwater)EPE: 0.52 -> 0.55Hurt
add terrestrial KITTI to SceneFlowIGEV++ · SquidEPE: 2.18 -> 2.02No clear effect
enable left-right consistency module in generation (ablation)stereo data generation · UWStereoEPE: 3.237 -> 2.953Improved
enable LR-consistency module (ablation)stereo data generation · UWStereoBreak px: 15 -> 5Improved
add cross-domain self-distillation (parameter-disjoint) (ablation)IGEV++ · UWStereo TotalEPE: 2.9530 -> 2.7510Improved
add clean-branch supervision with shared pseudo target (ablation)self-distillation · UWStereo TotalEPE: 2.7510 -> 2.6350Improved
add L2 regularization to self-distillation (ablation)self-distillation · UWStereo TotalEPE: 2.7510 -> 3.0510Hurt
share extractor, refinement or aggregation between teacher and student (ablation)self-distillation · UWStereo TotalEPE: 2.7510 -> 2.7200No clear effect
replace IGEV++ backbone with perception frames + video encoder + DINOv2 (ablation)IGEV++ · UWStereo TotalEPE: 2.9530 -> 2.4830Improved
replace encoder with VGG19+DINOv2 (without perception frames) (ablation)IGEV++ · UWStereo TotalEPE: 2.9530 -> 3.0790Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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