About¶

Acknowledgments¶

ViPE is built on top of many open-source research projects and codebases, including:

• DROID-SLAM
• Depth Anything V2
• Depth Anything 3
• Metric3Dv2
• PriorDA
• UniDepth
• UniK3D
• VideoDepthAnything
• GeoCalib
• Segment and Track Anything

See THIRD_PARTY_LICENSES.md for the full license list.

We thank Aigul Dzhumamuratova, Viktor Kuznetsov, Soha Pouya, and Ming-Yu Liu for useful discussions, and Vishal Kulkarni for release support.

Citation¶

If you find ViPE useful in your research or application, please cite:

@inproceedings{huang2025vipe,
    title={ViPE: Video Pose Engine for 3D Geometric Perception},
    author={Huang, Jiahui and Zhou, Qunjie and Rabeti, Hesam and Korovko, Aleksandr and Ling, Huan and Ren, Xuanchi and Shen, Tianchang and Gao, Jun and Slepichev, Dmitry and Lin, Chen-Hsuan and Ren, Jiawei and Xie, Kevin and Biswas, Joydeep and Leal-Taixe, Laura and Fidler, Sanja},
    booktitle={NVIDIA Research Whitepapers arXiv:2508.10934},
    year={2025}
}

License¶

This project downloads and installs additional third-party models and software that are not distributed by NVIDIA. Review the license terms of those models and projects before use.

The ViPE source code, except for the UniK3D part, is released under the Apache 2.0 License. The UniK3D portion is under the BY-NC-SA 4.0 license.