SAM 3能根据概念提示精准分割追踪图像视频中的物体。
SAM 3: Segment Anything with Concepts
- 用概念提示（名词短语或图像样例）实现统一的检测、分割与追踪。
- 在400万独特概念标签数据上训练，准确率比现有系统提升一倍。
- 适合需要跨模态理解与动态物体追踪的研究者与开发者。
我们提出Segment Anything Model (SAM) 3，一种基于概念提示（如“黄色校车”、图像样例或二者结合）在图像和视频中检测、分割与追踪物体的统一模型。提示式概念分割（PCS）接收此类提示并返回所有匹配实例的分割掩码和唯一身份。为推动PCS发展，我们构建了可扩展的数据引擎，生成包含400万独特概念标签（含难负样本）的高质量数据集。模型由图像级检测器与基于记忆的视频追踪器组成，共享单一主干网络。识别与定位解耦，通过存在头显著提升检测精度。SAM 3在图像和视频PCS任务中准确率均翻倍，并超越先前SAM在视觉分割任务的表现。我们开源SAM 3及新提出的SA-Co基准测试数据集。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。