Researchers at the University of Tübingen have released 3D-RE-GEN, a generative framework that reconstructs a complete, editable indoor scene from a single photograph, rebuilding individual objects and their backgrounds as textured 3D assets with consistent lighting and geometry. The project, formally titled *3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework*, was authored by Tobias Sautter, Jan-Niklas Dihlmann and Hendrik P.A. Lensch of the university's Computer Graphics Group, and posted to arXiv on December 19, 2025 (arXiv:2512.17459). It is slated for a poster presentation at CVPR 2026.
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.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.