Singapore's Show Lab at the National University of Singapore (NUS) has released "RobotSeg," the first foundation model that segments robot arms, grippers, and whole robots at high accuracy in both images and video. Built on top of Meta's SAM 2, it has been accepted as an Oral presentation at CVPR 2026, a leading computer vision conference. Code and models are available on GitHub, and the paper is on arXiv.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.