"Segment Anything" model uses image segmentation to isolate objects on command. This could really open rotoscoping to those mortals who cannot sit down at a keyboard and monitor for hours at a time.
On Wednesday, Meta announced an AI model called the Segment Anything Model (SAM) that can identify individual objects in images and videos, even those not encountered during training, reports Reuters.
Results that may be inaccessible to you are currently showing.
Hide inaccessible results