Carion et al.: SAM 3 promptable concept segmentation

What changed

Unified text/exemplar-prompted detection, segmentation and video tracking with decoupled recognition/localization, a scalable data engine and the companion SA-Co evaluation benchmark.

Scientific scope

Unified text/exemplar-prompted detection, segmentation and video tracking with decoupled recognition/localization, a scalable data engine and the companion SA-Co evaluation benchmark. One model/task/data contribution, not a separate record per image/video mode. Open-vocabulary concepts and finite evaluation gains do not guarantee every concept can be segmented. Original 2025 report excludes later SAM3.1 updates.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. One model/task/data contribution, not a separate record per image/video mode. Open-vocabulary concepts and finite evaluation gains do not guarantee every concept can be segmented. Original 2025 report excludes later SAM3.1 updates.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• SAM 3: Segment Anything with Concepts
• Carion et al.: SAM 3 promptable concept segmentation — official research record

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction