SAM 3：基于概念的分割万物

摘要

我们推出第三代分割一切模型（SAM 3），这是一个基于概念提示的统一模型，能够检测、分割并追踪图像和视频中的目标对象。我们将概念提示定义为简短名词短语（如"黄色校车"）、图像示例或二者的组合。可提示概念分割（PCS）技术接收此类提示后，可为所有匹配的目标实例返回分割掩码和唯一标识符。为推进PCS技术发展，我们构建了可扩展的数据引擎，生成包含400万个独特概念标签的高质量数据集，涵盖图像和视频中的困难负样本。我们的模型由共享单一骨干网的图像级检测器和基于记忆的视频追踪器组成，通过独立的存在性检测头实现识别与定位解耦，从而提升检测精度。SAM 3在图像和视频PCS任务中的准确率均达到现有系统的两倍，并提升了前代SAM在视觉分割任务中的性能。我们开源了SAM 3模型及全新的概念化分割一切基准（SA-Co），用于可提示概念分割研究。

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.

SAM 3：基于概念的分割万物

SAM 3: Segment Anything with Concepts

摘要

Support