SAM 3：基於概念的萬物分割

摘要

我們推出Segment Anything Model（SAM）3，這是一個基於概念提示的統一模型，能夠在圖像和影片中檢測、分割和追蹤物體。概念提示定義為簡短名詞短語（如「黃色校車」）、圖像範例或兩者組合。可提示概念分割（PCS）接收此類提示，並返回所有匹配物體實例的分割遮罩與唯一識別碼。為推進PCS技術，我們構建了可擴展的數據引擎，生成包含400萬個獨特概念標籤的高質量數據集，涵蓋圖像與影片中的困難負樣本。我們的模型由共享單一骨幹網路的圖像級檢測器和基於記憶的影片追蹤器組成，透過獨立的存在性預測頭解耦識別與定位任務，從而提升檢測精度。SAM 3在圖像與影片PCS任務中的準確率較現有系統提升一倍，並強化了前代SAM在視覺分割任務的性能。我們將開源SAM 3模型及用於可提示概念分割的新基準「Segment Anything with Concepts（SA-Co）」。

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：基於概念的萬物分割

SAM 3: Segment Anything with Concepts

摘要

Support