AirZoo is a new dataset covering 378 regions across 22 countries with pixel-level metric depth and 6-DoF poses, shown via benchmarks to improve SoTA models on aerial image retrieval, cross-view matching, and multi-view 3D reconstruction.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
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.
citing papers explorer
-
AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision
AirZoo is a new dataset covering 378 regions across 22 countries with pixel-level metric depth and 6-DoF poses, shown via benchmarks to improve SoTA models on aerial image retrieval, cross-view matching, and multi-view 3D reconstruction.
-
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.