SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. Compared to its predecessor SAM 2, SAM 3 introduces the ability to exhaustively segment all instances of an open vocabulary concept specified by a short text phrase or exemplars. Unlike prior work, SAM 3 can handle a vastly larger set of open vocabulary prompts. It achieves 75 80% of human performance on our new SA CO benchmark which contains 270K unique concepts, over 50 times more than existing benchmarks. Hugging Face 🤗 app Basic Usage The official code is publicly released in the sam3 repo. Usage with 🤗 Transformers SAM3 Promptable Concept Segmentation (PCS) for Images SAM3 performs Promptable Concept Segmentation (PCS) on images, taking text and/or image exemplars as prompts and returning segmentation masks for all matching object instances in the image. Text Only Prompts You can display masks using a simple helper like the following: Then you can save the resulting composite image or display it in a notebook: Single Bounding Box Prompt Segment objects using a bounding box: Multiple Box…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy