Visual Geometry Grounded Transformer (VGGT, CVPR 2025) is a feed-forward neural network that directly infers all key 3D attributes of a scene, including extrinsic and intrinsic camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views, within seconds.
If you find our repository useful, please consider giving it a star ⭐ and citing our paper in your work:
1@inproceedings{wang2025vggt,
2 title={VGGT: Visual Geometry Grounded Transformer},
3 author={Wang, Jianyuan and Chen, Minghao and Karaev, Nikita and Vedaldi, Andrea and Rupprecht, Christian and Novotny, David},
4 booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
5 year={2025}
6}
