taesiri
Abstract
Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.
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.
Community
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.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3 (2025)
- SAM-DAQ: Segment Anything Model with Depth-guided Adaptive Queries for RGB-D Video Salient Object Detection (2025)
- UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity (2025)
- 2nd Place Report of MOSEv2 Challenge 2025: Concept Guided Video Object Segmentation via SeC (2025)
- NOVO: Bridging LLaVA and SAM with Visual-only Prompts for Reasoning Segmentation (2025)
- Unified Open-World Segmentation with Multi-Modal Prompts (2025)
- Temporal Prompting Matters: Rethinking Referring Video Object Segmentation (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper