SAM 2: Segment Anything in Images and Videos

TLDR

We present Segment Anything Model 2 (SAM 2), a foundation model aimed at promptable visual segmentation in images and videos. SAM 2 is built on a data engine that gathers the largest video segmentation dataset to date and employs a simple transformer architecture with streaming memory for real‑time video processing. SAM 2 achieves strong performance across tasks, outperforming prior methods with 3× fewer interactions in video segmentation, delivering 6× faster and more accurate image segmentation than SAM, and is released with its dataset and an interactive demo.

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 a version of our model, the dataset and an interactive demo.