A research team at Seoul National University's (SNU) VGILab has released Extend3D, a training-free pipeline that generates town-scale 3D scenes from a single image. The code is distributed on GitHub under the MIT license and is based on a paper accepted at CVPR 2026 (Yoon et al.).
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.