Sam Apr 2026

The follow-up paper, "SAM 2: Segment Anything in Images and Videos," extends the model to handle video objects in real-time.

Depending on your field, you might be looking for these "proper" adaptations: The follow-up paper, "SAM 2: Segment Anything in

The first paper, "Segment Anything," introduced the concept of a promptable segmentation system and the massive SA-1B dataset. The follow-up paper

The most recent advancement, "SAM 3: Segment Anything with Concepts," unifies detection, segmentation, and tracking with text and visual prompts. Specialized "SAM" Papers "SAM 3: Segment Anything with Concepts