SAM 2: Segment Anything in Images and Videos
Abstract
We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Our model is a simple transformer architecture with streaming memory for real-time video processing. SAM 2 trained on our data provides strong performance across a wide range of tasks. In video segmentation, we observe better accuracy, using 3x fewer interactions than prior approaches. In image segmentation, our model is more accurate and 6x faster than the Segment Anything Model (SAM). We believe that our data, model, and insights will serve as a significant milestone for video segmentation and related perception tasks. We are releasing our main model, the dataset, an interactive demo and code.
Cite
Text
Ravi et al. "SAM 2: Segment Anything in Images and Videos." International Conference on Learning Representations, 2025.Markdown
[Ravi et al. "SAM 2: Segment Anything in Images and Videos." International Conference on Learning Representations, 2025.](https://mlanthology.org/iclr/2025/ravi2025iclr-sam/)BibTeX
@inproceedings{ravi2025iclr-sam,
title = {{SAM 2: Segment Anything in Images and Videos}},
author = {Ravi, Nikhila and Gabeur, Valentin and Hu, Yuan-Ting and Hu, Ronghang and Ryali, Chaitanya and Ma, Tengyu and Khedr, Haitham and Rädle, Roman and Rolland, Chloe and Gustafson, Laura and Mintun, Eric and Pan, Junting and Alwala, Kalyan Vasudev and Carion, Nicolas and Wu, Chao-Yuan and Girshick, Ross and Dollar, Piotr and Feichtenhofer, Christoph},
booktitle = {International Conference on Learning Representations},
year = {2025},
url = {https://mlanthology.org/iclr/2025/ravi2025iclr-sam/}
}