Infinite Photorealistic Worlds Using Procedural Generation
Alexander Raistrick, Lahav Lipson, Zeyu Ma, Lingjie Mei, Mingzhe Wang, Yiming Zuo, Karhan Kayan, Hongyu Wen
Abstract
We introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from scratch via randomized mathematical rules, using no external source and allowing infinite variation and composition. Infinigen offers broad coverage of objects and scenes in the natural world including plants, animals, terrains, and natural phenomena such as fire, cloud, rain, and snow. Infinigen can be used to generate unlimited, diverse training data for a wide range of computer vision tasks including object detection, semantic segmentation, optical flow, and 3D reconstruction. We expect Infinigen to be a useful resource for computer vision research and beyond. Please visit https://infinigen.org for videos, code and pre-generated data.
BibTeX
@inproceedings{cvpr2023_infinitephotorea,
title = {Infinite Photorealistic Worlds Using Procedural Generation},
author = {Alexander Raistrick and Lahav Lipson and Zeyu Ma and Lingjie Mei and Mingzhe Wang and Yiming Zuo and Karhan Kayan and Hongyu Wen and Beining Han and Yihan Wang and Alejandro Newell and Hei Law and Ankit Goyal and Kaiyu Yang and Jia Deng},
booktitle = {CVPR 2023},
year = {2023}
}