VGGT
VGGT (Visual Geometry Grounded Transformer)
CVPR 2025 Best Paper: geometry without the geometry pipeline
Latest: VGGT (CVPR 2025)
CVPR 2025 Best Paper winner from Meta AI and Oxford's Visual Geometry Group: a single feed-forward transformer that infers camera parameters, depth maps, point maps, and 3D point tracks from one to hundreds of images in seconds — replacing whole classical structure-from-motion pipelines with one network pass. Code is open source.
Why it matters
VGGT replaced the classical structure-from-motion pipeline with one feed-forward transformer that infers cameras, depth, point maps and tracks from one to hundreds of images in seconds. Chosen Best Paper from over 13,000 CVPR 2025 submissions, it reset expectations for how much 3D geometry a single network pass can recover.
Facts
- Picked as the top paper out of more than 13,000 CVPR submissions; reconstructs scenes in seconds where optimization-based SfM takes minutes to hours.
Try it yourself
Try it in the Hugging Face Space ↗ VGGT-1B on Hugging Face ↗ Read the paper ↗
Sources
arXiv ↗GitHub · vggt ↗cs.ox.ac.uk ↗