SAM 3: Segment Anything with Concepts

TL;DR

SAM 3 is a unified model for object detection, segmentation, and tracking in images and videos based on flexible concept prompts, significantly improving accuracy over previous systems.

Contribution

It introduces a scalable dataset with 4 million concept labels and a novel model architecture that enhances promptable concept segmentation accuracy.

Findings

SAM 3 doubles the accuracy of existing systems in image and video concept segmentation.

It improves previous SAM capabilities on visual segmentation tasks.

The model is open source along with a new benchmark for promptable concept segmentation.

Abstract

We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., "yellow school bus"), image exemplars, or a combination of both. Promptable Concept Segmentation (PCS) takes such prompts and returns segmentation masks and unique identities for all matching object instances. To advance PCS, we build a scalable data engine that produces a high-quality dataset with 4M unique concept labels, including hard negatives, across images and videos. Our model consists of an image-level detector and a memory-based video tracker that share a single backbone. Recognition and localization are decoupled with a presence head, which boosts detection accuracy. SAM 3 doubles the accuracy of existing systems in both image and video PCS, and improves previous SAM capabilities on visual segmentation tasks. We open source SAM 3 along with our new Segment Anything with Concepts (SA-Co) benchmark for promptable concept segmentation.