SAM 2: Segment Anything in Images and Videos
This work addresses segmentation challenges for computer vision applications, representing an incremental improvement over prior models.
The authors tackled promptable visual segmentation in images and videos by developing SAM 2, a foundation model that achieves better accuracy with 3x fewer interactions in video segmentation and is 6x faster and more accurate than its predecessor in image segmentation.
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.