# "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.

- Published: 2026-10-08T06:25:29.519Z
- Canonical: https://polylog.news/ai/2026-10-08/building-rome-from-a-single-image-generates-complete-3d-scen
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [arXiv](https://arxiv.org/abs/2610.08790), [Hugging Face Papers](https://huggingface.co/papers/2610.08790)

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…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-08/building-rome-from-a-single-image-generates-complete-3d-scen (subscription information: https://polylog.news/pricing).