Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation

التفاصيل البيبلوغرافية
العنوان: Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation
المؤلفون: Raistrick, Alexander, Mei, Lingjie, Kayan, Karhan, Yan, David, Zuo, Yiming, Han, Beining, Wen, Hongyu, Parakh, Meenal, Alexandropoulos, Stamatis, Lipson, Lahav, Ma, Zeyu, Deng, Jia
سنة النشر: 2024
المجموعة: Computer Science
مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition
الوصف: We introduce Infinigen Indoors, a Blender-based procedural generator of photorealistic indoor scenes. It builds upon the existing Infinigen system, which focuses on natural scenes, but expands its coverage to indoor scenes by introducing a diverse library of procedural indoor assets, including furniture, architecture elements, appliances, and other day-to-day objects. It also introduces a constraint-based arrangement system, which consists of a domain-specific language for expressing diverse constraints on scene composition, and a solver that generates scene compositions that maximally satisfy the constraints. We provide an export tool that allows the generated 3D objects and scenes to be directly used for training embodied agents in real-time simulators such as Omniverse and Unreal. Infinigen Indoors is open-sourced under the BSD license. Please visit https://infinigen.org for code and videos.
Comment: Accepted to CVPR 2024
نوع الوثيقة: Working Paper
URL الوصول: http://arxiv.org/abs/2406.11824
رقم الأكسشن: edsarx.2406.11824
قاعدة البيانات: arXiv