The Segment Anything Model (SAM) produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been trained on a dataset of 11 million images and 1.1 billion masks, and has strong zero-shot performance on a variety of segmentation tasks.

In addition to the new model, Meta AI is also releasing the SA-1B dataset, which is 400x larger than any existing segmentation dataset —they hope this work will help accelerate computer vision research and enable entirely new applications.