SAM 3.1: Faster and More Accessible Real-Time Video Detection and Tracking With Multiplexing and Global Reasoning
Summary
Meta AI releases SAM 3.1, an update to the Segment Anything Model that enhances real-time video detection and tracking through multiplexing and global reasoning capabilities.
Similar Articles
Segment Anything Model (SAM) 3.1 (2 minute read)
SAM 3.1 can detect, segment, and track objects in images and video using text prompts on the Meta Model API, with specified inference costs.
SAM 3: Segment Anything with Concepts
SAM 3 introduces a unified model for promptable concept segmentation and tracking, achieving state-of-the-art performance with a decoupled recognition and localization architecture and a scalable data engine.
@skalskip92: there's no catch; SAM3 is open source and really good one of the things it does really well is object tracking, even in…
SAM3 (Segment Anything Model 3) is open source and performs exceptionally well at object tracking even in complex scenes like basketball, making it a standout computer vision model.
SAM-MT: Real-Time Interactive Multi-Target Video Segmentation
This paper introduces SAM-MT, an extension of SAM2 for real-time interactive multi-target video segmentation, achieving high FPS independent of target count.
facebook/sam3
Meta 发布 SAM 3，一个统一的图像与视频可提示分割基础模型，支持文本或视觉提示进行检测、分割与跟踪，并首次可穷举分割开放词汇概念的所有实例，在新的 SA-CO 基准上达到人类表现的 75-80%。