SAM 2: Segment Anything in Images and Videos
arXiv:2408.00714
Abstract
We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Our model is a simple transformer architecture with streaming memory for real-time video processing. SAM 2 trained on our data provides strong performance across a wide range of tasks. In video segmentation, we observe better accuracy, using 3x fewer interactions than prior approaches. In image segmentation, our model is more accurate and 6x faster than the Segment Anything Model (SAM). We believe that our data, model, and insights will serve as a significant milestone for video segmentation and related perception tasks. We are releasing our main model, dataset, as well as code for model training and our demo.
Website: https://ai.meta.com/sam2
Cited by in corpus (9)
- UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
- Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization
- SinkSAM-Net: Knowledge-Driven Self-Supervised Sinkhole Segmentation Using Topographic Priors and Segment Anything Model
- Group Gaze-Sharing with Projection Displays
- Generalist Models in Medical Image Segmentation: A Survey and Performance Comparison with Task-Specific Approaches
- Enhancing Cell Instance Segmentation in Scanning Electron Microscopy Images via a Deep Contour Closing Operator
- SAMRI-2: A Memory-based Model for Cartilage and Meniscus Segmentation in 3D MRIs of the Knee Joint
- Training-Free, Identity-Preserving Image Editing for Fashion Pose Alignment and Normalization
- Deep Learning for Accurate Vision-based Catch Composition in Tropical Tuna Purse Seiners