https://infinigen.org/

Skip to main content
 
Infinigen LogoInfinigen Logo
GitHubContributingData Download
 
[random_sam]
[random_sam]

About Infinigen

Infinigen is a procedural generator of 3D scenes, developed by
Princeton Vision & Learning Lab. Infinigen is optimized for computer
vision research and generates diverse high-quality 3D training data.
Infinigen is based on Blender and is free and open-source (BSD
3-Clause License). Infinigen is being actively developed to expand
its capabilities and coverage. Everyone is welcome to contribute.

Research Papers

Infinite Photorealistic Worlds using Procedural Generation

Alexander Raistrick*, Lahav Lipson*, Zeyu Ma*  Lingjie Mei, Mingzhe
Wang, Yiming Zuo, Karhan Kayan, Hongyu Wen, Beining HanYihan Wang,
Alejandro Newell, Hei Law, Ankit Goyal, Kaiyu Yang, Jia Deng
( *equal contribution, alphabetical order )
Conference on Computer Vision and Pattern Recognition (CVPR) 2023
[paper]Read the paper

@inproceedings{infinigen2023infinite,
  title={Infinite Photorealistic Worlds Using Procedural Generation},
  author={Raistrick, Alexander and Lipson, Lahav and Ma, Zeyu and Mei, Lingjie and Wang, Mingzhe and Zuo, Yiming and Kayan, Karhan and Wen, Hongyu and Han, Beining and Wang, Yihan and Newell, Alejandro and Law, Hei and Goyal, Ankit and Yang, Kaiyu and Deng, Jia},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={12630--12641},
  year={2023}
}

Infinigen Indoors: Photorealistic Indoor Scenes using Procedural
Generation

Alexander Raistrick*, Lingjie Mei*, Karhan Kayan*, David Yan,Yiming
Zuo, Beining Han, Hongyu Wen, Meenal Parakh, Stamatis Alexandropoulos
, Lahav Lipson, Zeyu Ma, Jia Deng
( *equal contribution, random order )
Conference on Computer Vision and Pattern Recognition (CVPR) 2024
[paper]Read the paper

@inproceedings{infinigen2024indoors,
    author={Raistrick, Alexander and Mei, Lingjie and Kayan, Karhan and Yan, David and Zuo, Yiming and Han, Beining and Wen, Hongyu and Parakh, Meenal and Alexandropoulos, Stamatis and Lipson, Lahav and Ma, Zeyu and Deng, Jia},
    title={Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month={June},
    year={2024},
    pages={21783-21794}
}

Key Features & Capabilities

[procedural]

Procedural

Infinigen is a procedural generator that creates everything entirely
from randomized mathematical rules, including all shapes and
materials, from macro structures to micro details. Infinigen can
create unlimited variations. Users have full control the generation
of assets by overriding default parameters of randomization.

[diverse]

Diverse

Infinigen provides generators for diverse objects and scenes in the
natural world including plants, animals, terrains, and natural
phenomena such as fire, cloud, rain, and snow. The current focus on
nature is motivated by the observation that mammalian vision evolved
in the natural world. However, Infinigen is expected to expand over
time to cover built environments and artificial objects.

[fake_geo]
Fake Geometry
[real_geo]
Real Geometry

Real Geometry

Infinigen is optimized for computer vision research, particularly 3D
vision. Infinigen does not use bump/normal-maps, full-transparency,
or other techniques which fake geometric detail. All fine details of
geometry from Infinigen are real, ensuring accurate 3D ground truth.

[quad]

Automatic Annotations

Infinigen can automatically generate high-quality annotations for a
variety of computer vision tasks, including optical flow, 3D scene
flow, depth, surface normals, panoptic segmentation, occlusion
boundaries. Because users have full access to the rendering process,
the annotations are easily customizable.

Community

  * Twitter

More

  * GitHub

Copyright (c) 2024 Infinigen