MetaAI: Introducing Segment Anything: Working toward the first foundation model for image segmentation

Impressive! Looks like image segmentation is becoming a breeze! It may be a breakthrough!

I have not yet read the paper. The two senior authors of this paper, i.e. Piotr Dollar & Ross Girshick, are well known and first rated computer vision researchers!

"Today, we aim to democratize segmentation by introducing the Segment Anything project: a new task, dataset, and model for image segmentation, as we explain in our research paper. We are releasing both our general Segment Anything Model (SAM) and our Segment Anything 1-Billion mask dataset (SA-1B), the largest ever segmentation dataset, to enable a broad set of applications and foster further research into foundation models for computer vision. We are making the SA-1B dataset available for research purposes and the Segment Anything Model is available under a permissive open license (Apache 2.0). ...
In the AR/VR domain, SAM could enable selecting an object based on a user’s gaze and then “lifting” it into 3D."

Introducing Segment Anything: Working toward the first foundation model for image segmentation

Segment Anything (open access)

Credits: Marktechpost AI Newsletter