SAM 2: Segment Anything in Images and Videos

By Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya K. Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloé Rolland, Laura Gustafson and 8 more. International Conference on Learning Representations, 2024

3,755 citations recorded by the source corpus.

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, dataset, as well as code for model training and our demo.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/92a09cdfc19f3f582d89c28c1b4f386299cc69e1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Chunrui Han
2. Xiangyu Zhang
3. Zeyinzi Jiang
4. Yuang Peng
5. Chaojie Mao
6. Rui Wang
7. Zhen Han
8. Yulin Pan

Citations in the corpus

• VACE: All-in-One Video Creation and Editing (2025, positive): “Furthermore, we employ the propagate operation of SAM2 [52] for video segmentation to obtain instance-level information across the video.”
• AgiBot World Colosseo: A Large-Scale Manipulation Platform for Scalable and Intelligent Embodied Systems (2025, neutral): “A suite of 100 dual-arm humanoid robots is deployed.”
• Step1X-Edit: A Practical Framework for General Image Editing (2025, positive): “We then apply SAM-2 [46] for segmentation and use ObjectRemovalAlpha [30] to perform inpainting.”