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
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext aa03b1e4-6ced-4ac3-980d-e1cc6d8b7846Cited by top-tier papers48
- SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender CodeZiniu Hu, Ahmet Iscen, Aashi Jain, Thomas Kipf et al.ICML 2024 · 105 citations
- Trace Anything: Representing Any Video in 4D via Trajectory FieldsXinhang Liu, Yuxi Xiao, Donny Y. Chen, Jiashi Feng et al.ICLR 2026 · 38 citations
- XCube: Large-Scale 3D Generative Modeling using Sparse Voxel HierarchiesXuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth et al.CVPR 2024 · 32 citations
- Make-A-Shape: a Ten-Million-scale 3D Shape ModelKa-Hei Hui, Aditya Sanghi, Arianna Rampini, Kamal Rahimi Malekshan et al.ICML 2024 · 29 citations
- MatFuse: Controllable Material Generation with Diffusion ModelsGiuseppe Vecchio, Renato Sortino, Simone Palazzo, Concetto SpampinatoCVPR 2024 · 26 citations
Builds on17
- DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D CamerasZachary Teed, Jia DengNeurIPS 2021 · 1,248 citations
- Habitat 2.0: Training Home Assistants to Rearrange their HabitatAndrew Szot, Alexander Clegg, Eric Undersander, Erik Wijmans et al.NeurIPS 2021 · 826 citations
- Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene UnderstandingMike Roberts, Jason Ramapuram, Anurag Ranjan, Atulit Kumar et al.ICCV 2021 · 633 citations
- 🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural GenerationMatt Deitke, Eli VanderBilt, Alvaro Herrasti, Luca Weihs et al.NeurIPS 2022 · 596 citations
- 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTicsHuan Fu, Bowen Cai, Lin Gao, Lingxiao Zhang et al.ICCV 2021 · 419 citations
Related papers
- Infinigen Indoors: Photorealistic Indoor Scenes using Procedural GenerationAlexander Raistrick, Lingjie Mei, Karhan Kayan, David Yan et al.CVPR 2024 · 24 citations
- InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene ComplexityHaoming Wang, Qiyao Xue, Wei GaoCVPR 2026 · 6 citations
- Patch-Based 3D Natural Scene Generation from a Single ExampleWeiyu Li, Xuelin Chen, Jue Wang, Baoquan ChenCVPR 2023
- InfiniCity: Infinite-Scale City SynthesisChieh Hubert Lin, Hsin-Ying Lee, Willi Menapace, Menglei Chai et al.ICCV 2023 · 86 citations
- InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain GenerationAlexander GoslinSIGGRAPH 2026
