Fig.1

Concept

SAM2

SAM2 (Segment Anything Model 2) is Meta's promptable segmentation model, extending the original SAM from still images to video. Like SAM, you give it a prompt (a point, box, or mask) and it returns a segmentation mask for the indicated object.

The rest of “SAM2” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library