Overview
Segment Anything, or SAM, is a promptable image-segmentation model from Meta AI Research. It can generate masks from foreground or background points, boxes, or an automatic scan of an image, and the repository includes inference code, checkpoints, and example notebooks. The project is intended for researchers and developers building image-processing workflows with Python and PyTorch. The original implementation is released under Apache-2.0. Its repository points users toward newer Segment Anything releases, and the last meaningful push is older than 12 months, so this original entry is marked unmaintained.