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
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper48
- SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender CodeZiniu Hu, Ahmet Iscen, Aashi Jain, Thomas Kipf 等ICML 2024 · 被引用 105 次
- Trace Anything: Representing Any Video in 4D via Trajectory FieldsXinhang Liu, Yuxi Xiao, Donny Y. Chen, Jiashi Feng 等ICLR 2026 · 被引用 38 次
- XCube: Large-Scale 3D Generative Modeling using Sparse Voxel HierarchiesXuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth 等CVPR 2024 · 被引用 32 次
- Make-A-Shape: a Ten-Million-scale 3D Shape ModelKa-Hei Hui, Aditya Sanghi, Arianna Rampini, Kamal Rahimi Malekshan 等ICML 2024 · 被引用 29 次
- MatFuse: Controllable Material Generation with Diffusion ModelsGiuseppe Vecchio, Renato Sortino, Simone Palazzo, Concetto SpampinatoCVPR 2024 · 被引用 26 次
它引用的顶会 Paper17
- DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D CamerasZachary Teed, Jia DengNeurIPS 2021 · 被引用 1,248 次
- Habitat 2.0: Training Home Assistants to Rearrange their HabitatAndrew Szot, Alexander Clegg, Eric Undersander, Erik Wijmans 等NeurIPS 2021 · 被引用 826 次
- Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene UnderstandingMike Roberts, Jason Ramapuram, Anurag Ranjan, Atulit Kumar 等ICCV 2021 · 被引用 633 次
- 🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural GenerationMatt Deitke, Eli VanderBilt, Alvaro Herrasti, Luca Weihs 等NeurIPS 2022 · 被引用 596 次
- 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTicsHuan Fu, Bowen Cai, Lin Gao, Lingxiao Zhang 等ICCV 2021 · 被引用 419 次
相关 Paper
- Infinigen Indoors: Photorealistic Indoor Scenes using Procedural GenerationAlexander Raistrick, Lingjie Mei, Karhan Kayan, David Yan 等CVPR 2024 · 被引用 24 次
- InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene ComplexityHaoming Wang, Qiyao Xue, Wei GaoCVPR 2026 · 被引用 6 次
- 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 等ICCV 2023 · 被引用 86 次
- InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain GenerationAlexander GoslinSIGGRAPH 2026
