facebook/EdgeTAM

Model Details

[📃 Tech Report] [📂 Github] [🤗 Demo]

EdgeTAM is an on-device executable variant of the SAM 2 for promptable segmentation and tracking in videos. It runs 22× faster than SAM 2 and achieves 16 FPS on iPhone 15 Pro Max without quantization.

How to use

We provide the inference code with local deployment instructions in https://github.com/facebookresearch/EdgeTAM. You can find more details in the GitHub repo.

Citation

If you find our code useful for your research, please consider citing:

@article{zhou2025edgetam,
  title={EdgeTAM: On-Device Track Anything Model},
  author={Zhou, Chong and Zhu, Chenchen and Xiong, Yunyang and Suri, Saksham and Xiao, Fanyi and Wu, Lemeng and Krishnamoorthi, Raghuraman and Dai, Bo and Loy, Chen Change and Chandra, Vikas and Soran, Bilge},
  journal={arXiv preprint arXiv:2501.07256},
  year={2025}
}