Rui Zhu, Manmohan Chandraker, Kalyan Sunkavalli, Zexiang Xu, Zhengqin Li, Yannick Hold-Geoffroy, Miloš Hašan, Yu-Ying Yeh
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout. In this work, we go beyond this to propose PhotoScene 1 , 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2207.00757")
get_code_for_paper("2207.00757")
have("2207.00757")
Connect an agent — have() is free.