TerraSky3D: CVPR 2026 dataset pairs 50K aerial and ground images across 150 scenes

ducha_aiki · x · 2026-09-08

Researchers presented TerraSky3D at CVPR 2026: a dataset spanning 150 scenes with 50K images, 30 scenes featuring co-located aerial and ground imagery, targeting Image-to-3D, depth estimation, multi-view stereo, and SfM tasks with an aerial-to-ground cross-view focus on European landmarks.

Released under CC-BY-4.0 on Hugging Face (mattia-durso/TerraSky3D) in WebDataset TAR format, with an accompanying arXiv paper. Co-located aerial-ground pairs are a scarce resource for 3D reconstruction and sim2real research.

Original post →

More from Multimodal

Multimodal channel →