README.md

metadata

title: VGGT-Omega Demo
emoji: 🌀
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 5.50.0
app_file: app.py
python_version: '3.10'
hardware: zero-gpu
pinned: false
license: other
license_name: fair-noncommercial-research-license-v1
license_link: LICENSE
short_description: 3D reconstruction from images/video with VGGT-Omega
models:
  - facebook/VGGT-Omega

VGGT-Ω Demo

Interactive demo for VGGT-Ω, a feed-forward camera and depth reconstruction model from the Visual Geometry Group (Oxford) and Meta AI.

Upload images or a short video and the model returns a 3D point cloud with estimated camera poses, visualized as a GLB scene.

• Project page: https://vggt-omega.github.io/
• Source code: https://github.com/facebookresearch/vggt-omega
• Model card: https://huggingface.co/facebook/VGGT-Omega

Citation

@inproceedings{wang2026vggtomega,
  title={VGGT-{$\Omega$}},
  author={Wang, Jianyuan and Chen, Minghao and Zhang, Shangzhan and Karaev, Nikita and Sch{\"o}nberger, Johannes and Labatut, Patrick and Bojanowski, Piotr and Novotny, David and Vedaldi, Andrea and Rupprecht, Christian},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2026}
}

License

This demo is released under the FAIR Noncommercial Research License v1. See LICENSE.