SAM 2: Segment Anything in Images and Videos
Facebook · Google Deepmind · Meta AI · University of California, San Diego · Meta · University of California, Irvine · Sorbonne Université - Faculté des Sciences (Paris VI) · The Chinese University of Hong Kong · New York University · FAIR
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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.