PulseAugur
EN
LIVE 21:39:18

Meta AI releases SAM 3 for advanced image and video object tracking

Meta AI has released Segment Anything Model 3 (SAM 3), an advanced model for object detection, segmentation, and tracking in images and videos. This new version supports text, exemplar, and visual prompts, and includes model checkpoints, evaluation datasets, and fine-tuning code. Additionally, Meta has launched the Segment Anything Playground for easy experimentation and is integrating SAM 3 into products like Instagram and the Meta AI app. AI

IMPACT Enhances object detection and tracking capabilities, potentially accelerating real-time video analysis and media editing applications.

RANK_REASON New model release from a frontier lab with model weights, code, and a research paper. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on Meta AI blog →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Meta AI releases SAM 3 for advanced image and video object tracking

COVERAGE [1]

  1. Meta AI blog TIER_1 English(EN) ·

    Introducing Meta Segment Anything Model 3 and Segment Anything Playground