Infinite Photorealistic Worlds Using Procedural Generation

Alexander Raistrick; Lahav Lipson; Zeyu Ma; Lingjie Mei; Mingzhe Wang; Yiming Zuo; Karhan Kayan; Hongyu Wen; Beining Han; Yihan Wang; Alejandro Newell; Hei Law; Ankit Goyal; Kaiyu Yang; Jia Deng

doi:10.1109/CVPR52729.2023.01215

Infinite Photorealistic Worlds Using Procedural Generation

Alexander Raistrick, Lahav Lipson, Zeyu Ma, Lingjie Mei, Mingzhe Wang, Yiming Zuo, Karhan Kayan, Hongyu Wen, Beining Han, Yihan Wang, Alejandro Newell, Hei Law, Ankit Goyal, Kaiyu Yang, Jia Deng

Research output: Contribution to journal › Conference article › peer-review

37 Scopus citations

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 infinigen.org for videos, code and pre-generated data.

Original language	English (US)
Pages (from-to)	12630-12641
Number of pages	12
Journal	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2023-June
DOIs	https://doi.org/10.1109/CVPR52729.2023.01215
State	Published - 2023
Event	2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Vancouver, Canada Duration: Jun 18 2023 → Jun 22 2023

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition

Keywords

Datasets and evaluation

Access to Document

10.1109/CVPR52729.2023.01215

Cite this

Raistrick, A., Lipson, L., Ma, Z., Mei, L., Wang, M., Zuo, Y., Kayan, K., Wen, H., Han, B., Wang, Y., Newell, A., Law, H., Goyal, A., Yang, K., & Deng, J. (2023). Infinite Photorealistic Worlds Using Procedural Generation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2023-June, 12630-12641. https://doi.org/10.1109/CVPR52729.2023.01215

@article{4f45e9e00f8340109e90d17484401e31,

title = "Infinite Photorealistic Worlds Using Procedural Generation",

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 infinigen.org for videos, code and pre-generated data.",

keywords = "Datasets and evaluation",

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",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 ; Conference date: 18-06-2023 Through 22-06-2023",

year = "2023",

doi = "10.1109/CVPR52729.2023.01215",

language = "English (US)",

volume = "2023-June",

pages = "12630--12641",

journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

issn = "1063-6919",

publisher = "IEEE Computer Society",

}

Raistrick, A, Lipson, L, Ma, Z, Mei, L, Wang, M, Zuo, Y, Kayan, K, Wen, H, Han, B, Wang, Y, Newell, A, Law, H, Goyal, A, Yang, K & Deng, J 2023, 'Infinite Photorealistic Worlds Using Procedural Generation', Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2023-June, pp. 12630-12641. https://doi.org/10.1109/CVPR52729.2023.01215

TY - JOUR

T1 - Infinite Photorealistic Worlds Using Procedural Generation

AU - Raistrick, Alexander

AU - Lipson, Lahav

AU - Ma, Zeyu

AU - Mei, Lingjie

AU - Wang, Mingzhe

AU - Zuo, Yiming

AU - Kayan, Karhan

AU - Wen, Hongyu

AU - Han, Beining

AU - Wang, Yihan

AU - Newell, Alejandro

AU - Law, Hei

AU - Goyal, Ankit

AU - Yang, Kaiyu

AU - Deng, Jia

PY - 2023

Y1 - 2023

N2 - 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 infinigen.org for videos, code and pre-generated data.

AB - 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 infinigen.org for videos, code and pre-generated data.

KW - Datasets and evaluation

UR - http://www.scopus.com/inward/record.url?scp=85218187263&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85218187263&partnerID=8YFLogxK

U2 - 10.1109/CVPR52729.2023.01215

DO - 10.1109/CVPR52729.2023.01215

M3 - Conference article

AN - SCOPUS:85218187263

SN - 1063-6919

VL - 2023-June

SP - 12630

EP - 12641

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

Y2 - 18 June 2023 through 22 June 2023

ER -

Infinite Photorealistic Worlds Using Procedural Generation

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this