Meta Segment Anything Model 3(ai.meta.com)
630 points by lukeinator42 | 126 comments
Meta AI's landing page introducing Segment Anything Model 3 (SAM 3), which segments and tracks objects in images and videos from text and visual prompts.
#video-segmentation on Hacker News
2 stories tagged video-segmentation, newest first.
SAM 2: Segment Anything in Images and Videos(github.com)
674 points by xenova | 122 comments
GitHub repository from Meta's facebookresearch with inference code, model checkpoints, and example notebooks for Segment Anything Model 2 (SAM 2).