Morning Edition · Thursday, October 8, 2026Published at 2:25 AM EDT · New York

"Building Rome from a Single Image" generates complete 3D scene meshes, including unseen surfaces, from one photograph

The method uses distance-adaptive chunks and explicit labeling of observed versus unobserved regions, and it adds about 4,000 synthetic outdoor scenes to fix an indoor-heavy training data supply.

A new paper by Jiraphon Yenphraphai, Fang Li, Tianshuo Xu, Depu Meng, Quentin Herau, Yihan Hu, Raymond A. Yeh and Wei Zhan generates a complete 3D scene mesh from a single photograph, including surfaces the camera did not see. The research…