Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout. In this work, we go beyond this to propose PhotoScene, a framework that takes input image(s) of a scene along with approximately aligned CAD geometry (either reconstructed automatically or manually specified) and builds a photorealistic digital twin with high-quality materials and similar lighting. We model scene materials using procedural material graphs; such graphs represent photorealistic and resolution-independent materials. We optimize the parameters of these graphs and their texture scale and rotation, as well as the scene lighting to best match the input image via a differentiable rendering layer. We evaluate our technique on objects and layout reconstructions from ScanNet, SUN RGB-D and stock photographs, and demonstrate that our method reconstructs high-quality, fully relightable 3D scenes that can be re-rendered under arbitrary viewpoints, zooms and lighting.
@article{arxiv.2207.00757,
title = {PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes},
author = {Yu-Ying Yeh and Zhengqin Li and Yannick Hold-Geoffroy and Rui Zhu and Zexiang Xu and Miloš Hašan and Kalyan Sunkavalli and Manmohan Chandraker},
journal= {arXiv preprint arXiv:2207.00757},
year = {2022}
}
Comments
Accepted to CVPR 2022; Code is available at https://github.com/ViLab-UCSD/photoscene