Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation
Alexander Raistrick, Lingjie Mei, Karhan Kayan, David Yan, Yiming Zuo, Beining Han, Hongyu Wen, Meenal Parakh
Abstract
We introduce Infinigen Indoors a Blender-based procedural generator of photorealistic indoor scenes. It builds upon the existing Infinigen system which focuses on natural scenes but expands its coverage to indoor scenes by introducing a diverse library of procedural indoor assets including furniture architecture elements appliances and other day-to-day objects. It also introduces a constraint-based arrangement system which consists of a domain-specific language for expressing diverse constraints on scene composition and a solver that generates scene compositions that maximally satisfy the constraints. We provide an export tool that allows the generated 3D objects and scenes to be directly used for training embodied agents in real-time simulators such as Omniverse and Unreal. Infinigen Indoors is open-sourced under the BSD license. Please visit infinigen.org for code and videos.
BibTeX
@inproceedings{cvpr2024_infinigenindoors,
title = {Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation},
author = {Alexander Raistrick and Lingjie Mei and Karhan Kayan and David Yan and Yiming Zuo and Beining Han and Hongyu Wen and Meenal Parakh and Stamatis Alexandropoulos and Lahav Lipson and Zeyu Ma and Jia Deng},
booktitle = {CVPR 2024},
year = {2024}
}