Facebook Segment Anything - SAM

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.

Experience the model with the demo screen.

Model Details

The task of identifying which pixels in an image belong to an object, known as segmentation, is essential in computer vision and is utilized in a variety of fields, such as scientific image analysis and photo editing. However, developing an accurate segmentation model for specific tasks requires specialized technical expertise, access to AI training infrastructure, and a large amount of annotated in-domain data.

The Segment Anything project aims to minimize the requirement for task-specific modeling expertise, training compute, and custom data annotation for image segmentation. To achieve this, the project focuses on building a foundation model for image segmentation, which can adapt to specific tasks, similar to the way prompts are used in natural language processing models. The challenge lies in the fact that the necessary segmentation data is not readily available online or elsewhere, unlike images, videos, and text. Therefore, the Segment Anything project aims to create a segmentation dataset of unprecedented scale while developing a general, promptable segmentation model.

The Segment Anything model, known as SAM, has a general understanding of objects and can generate masks for any object in any image or video, including those it has not encountered before. SAM is versatile enough to cover a wide range of use cases and can be used immediately on new image "domains" such as underwater photos or cell microscopy, without requiring additional training, which is known as zero-shot transfer.

 title={Segment Anything}, 
 author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Doll{\'a}r, Piotr and Girshick, Ross},

Start now for free!

No contracts, no credit card.
Free up-to 100 frames
Free hands-on onboarding & support
Hundreds of applications wait for you