vggt

<div align="center">
<h1>VGGT: Visual Geometry Grounded Transformer</h1>

<a href="https://jytime.github.io/data/VGGT_CVPR25.pdf" target="_blank" rel="noopener noreferrer">
  <img src="https://img.shields.io/badge/Paper-VGGT" alt="Paper PDF">
</a>
<a href="https://arxiv.org/abs/2503.11651"><img src="https://img.shields.io/badge/arXiv-2503.11651-b31b1b" alt="arXiv"></a>
<a href="https://vgg-t.github.io/"><img src="https://img.shields.io/badge/Project_Page-green" alt="Project Page"></a>
<a href="https://huggingface.co/spaces/facebook/vggt"><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Demo-blue'></a>


**[Visual Geometry Group, University of Oxford](https://www.robots.ox.ac.uk/~vgg/)**; **[Meta AI](https://ai.facebook.com/research/)**


[Jianyuan Wang](https://jytime.github.io/), [Minghao Chen](https://silent-chen.github.io/), [Nikita Karaev](https://nikitakaraevv.github.io/), [Andrea Vedaldi](https://www.robots.ox.ac.uk/~vedaldi/), [Christian Rupprecht](https://chrirupp.github.io/), [David Novotny](https://d-novotny.github.io/)
</div>

```bibtex
@inproceedings{wang2025vggt,
  title={VGGT: Visual Geometry Grounded Transformer},
  author={Wang, Jianyuan and Chen, Minghao and Karaev, Nikita and Vedaldi, Andrea and Rupprecht, Christian and Novotny, David},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2025}
}
```

## Updates

- [May 18, 2026] The next step of VGGT — **VGGT-Omega** — has been released! Check it out at [https://vggt-omega.github.io/](https://vggt-omega.github.io/).


- [May 15, 2026] We fixed an implementation issue that was keeping redundant intermediate tensors in memory. With the same GPU memory budget, VGGT can now run on roughly 2-3x more input frames! See [VGGT-Omega](https://vggt-omega.github.io/) for more details.



- [July 29, 2025] We've updated the license for VGGT to permit **commercial use** (excluding military applications). All code in this repository is now under a commercial-use-friendly license. However, only the newly released checkpoint [**VGGT-1B-Commercial**](https://huggingface.co/facebook/VGGT-1B-Commercial) is licensed for commercial usage — the original checkpoint remains non-commercial. Full license details are available [here](https://github.com/facebookresearch/vggt/blob/main/LICENSE.txt). Access to the checkpoint requires completing an application form, which is processed by a system similar to LLaMA's approval workflow, automatically. The new checkpoint delivers similar performance to the original model. Please submit an issue if you notice a significant performance discrepancy.



- [July 6, 2025] Training code is now available in the `training` folder, including an example to finetune VGGT on a custom dataset. 


- [June 13, 2025] Honored to receive the Best Paper Award at CVPR 2025! Apologies if I’m slow to respond to queries or GitHub issues these days. If you’re interested, our oral presentation is available [here](http