Paper summary
Paper summary: SAM 2: Segment Anything in Images and Videos
SAM 2 extends Segment Anything to video with a streaming-memory Transformer and a data engine that built the largest video segmentation dataset to date.
- A streaming memory lets one simple Transformer segment objects through video in real time.
- The paper reports 3× fewer interactions than prior video methods, and image segmentation 6× faster than the original SAM.