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.
More from Multimodal
- Spatial-first AI video: map the scene with GPT-6 Astra before rendering — HeyZoyaKhan · 2026-09-09
- GPT-6 Astra codes geometry, Blender + Clay plugin renders, Dreamina finalizes footage — thetripathi58 · 2026-09-09
- Claude skips the training set: HTML/CSS rendered in a headless browser makes his site images — shashib · 2026-09-09
- A SpaceX homage built with Grok + Intangible shows AI 3D video creation in action — bilawalsidhu · 2026-09-09
- Marigold V2 launches at SIGGRAPH Asia 2026: sharp diffusion-transformer depth estimation — AntonObukhov1 · 2026-09-09
- AI-generated POV: riding a dragon through a medieval town — Brave-Wishbone-3650 · 2026-09-08