What is Meta Segment Anything Model 2 (SAM 2)?
Meta Segment Anything Model 2 (SAM 2) is a segmentation model that enables fast, precise selection of any object in any video or image.
Key Features of SAM 2
Segment any object, now in any video or image
SAM 2 is the first unified model for segmenting objects across images and videos. You can use a click, box, or mask as the input to select an object on any image or frame of video.
Robust segmentation, even in unfamiliar videos
SAM 2 is capable of strong zero-shot performance for objects, images and videos not previously seen during model training, enabling use in a wide range of real-world applications.
Real-time interactivity and results
SAM 2 is designed for efficient video processing with streaming inference to enable real-time, interactive applications.
State-of-the-art performance for object segmentation
SAM 2 outperforms the best models in the field for object segmentation in videos and images.
How to Use SAM 2
Track an object across any video interactively
Try the demo and track an object across any video interactively with as little as a single click on one frame, and create fun effects.
The Next Generation of Meta Segment Anything
SAM 2 brings state-of-the-art video and image segmentation capabilities into a single model, while preserving a simple design and fast inference speed.
Model Architecture
The SAM 2 model extends the promptable capability of SAM to the video domain by adding a per session memory module that captures information about the target object in the video.
The Segment Anything Video Dataset
A large and diverse video segmentation dataset, SAM 2 was trained on a large and diverse set of videos and masklets (object masks over time), created by applying SAM 2 interactively in a model in the loop data-engine.
Open Innovation
To enable the research community to build upon this work, we’re publicly releasing a pretrained Segment Anything 2 model, along with the SA-V dataset, a demo, and code.
Potential Model Applications
SAM 2 can be used by itself, or as part of a larger system with other models in future work to enable novel experiences.
Helpful Tips
- SAM 2 can be extended to take other types of input prompts such as in the future enabling creative ways of interacting with objects in real-time or live video.
- The video object segmentation outputs from SAM 2 could be used as input to other AI systems such as modern video generation models to enable precise editing capabilities.
Frequently Asked Questions
- How does SAM 2 work? SAM 2 is a segmentation model that enables fast, precise selection of any object in any video or image.
- What are the key features of SAM 2? SAM 2 has several key features, including segmenting any object in any video or image, robust segmentation, real-time interactivity and results, and state-of-the-art performance for object segmentation.
- How can I use SAM 2? You can try the demo and track an object across any video interactively with as little as a single click on one frame, and create fun effects.