A teacher-student semi-supervised framework adapts VGGT-based feed-forward 3D reconstruction to underwater environments using synthetic degraded on-land data and unlabeled real underwater video, achieving state-of-the-art underwater depth and point cloud estimation without any underwater 3D labels.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Wat3R: Underwater 3D Geometry Learning without Annotations
A teacher-student semi-supervised framework adapts VGGT-based feed-forward 3D reconstruction to underwater environments using synthetic degraded on-land data and unlabeled real underwater video, achieving state-of-the-art underwater depth and point cloud estimation without any underwater 3D labels.