Segment Anything 2
Foundation model for promptable visual segmentation in images and videos with streaming memory.
About
SAM 2 is a foundation model from Meta for promptable visual segmentation in both images and videos. It extends the original Segment Anything Model by treating images as single-frame videos and uses a transformer with streaming memory for real-time processing. The release ships with the SA-V dataset and shows strong performance across diverse tasks and visual domains.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Added
- May 7, 2026
Related Tools
Simple and effective multi-object tracking using every detection box.
Monocular depth estimation model producing detailed depth maps from single images.
End-to-end object detection with transformers by Meta, eliminating hand-designed components.
Self-supervised vision transformer by Meta producing universal visual features.
Unified vision foundation model by Microsoft for captioning, detection, and segmentation.
Robust multi-object tracking combining motion and appearance cues.