AI Paper Atlas

Research map / 3D vision / Depth and stereo

Wat3R: Underwater 3D Geometry Learning without Underwater Annotations

Jiangwei Ren, Xingyu Jiang, Zijie Song, Wei Xu, Hongkai Lin, Dingkang Liang, Xiang Bai

ECCV 2026 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry

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
adapt VGGT with Wat3R semi-supervised trainingVGGT · Sea-thru multi-view depthRel: 0.190 -> 0.167Improved
adapt VGGT with Wat3R semi-supervised trainingVGGT · FLSea Stereo multi-view depthRel: 0.137 -> 0.119Improved
adapt VGGT with Wat3RVGGT · Water3D point mapOverall mean: 0.624 -> 0.427Improved
adapt VGGT with Wat3RVGGT · SeaThru-NeRF poseAUC@5: 0.392 -> 0.540Improved
adapt VGGT with Wat3RVGGT · SeaThru-NeRF poseAUC@5: 0.540 vs 0.731 (DA3)Hurt
adapt VGGT with Wat3RVGGT · FLSea VI monocular depthRel: 0.107 -> 0.061Improved
apply underwater image enhancement before VGGT (Semi-UIR)VGGT · Sea-thru multi-view depthRel: 0.190 -> 0.201Hurt
apply underwater image enhancement before VGGT (PSPL)VGGT · FLSea Stereo multi-view depthRel: 0.137 -> 0.160Hurt
add synthetic underwater rendering training (ablation)VGGT · Sea-thru multi-view depthRel: 0.190 -> 0.173Improved
add real unlabeled underwater video to synthetic training (ablation)Wat3R ablation · Sea-thru multi-view depthRel: 0.173 -> 0.181Hurt
add real unlabeled underwater video to synthetic training (ablation)Wat3R ablation · FLSea Stereo multi-view depthRel: 0.135 -> 0.165Hurt
add strong augmentation with real video (ablation)Wat3R ablation · FLSea Stereo multi-view depthRel: 0.165 -> 0.126Improved

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