Infinigen Indoors：使用程序化生成的照片级真实感室内场景
Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation
AI总结：
本研究推出基于Blender的程序化室内场景生成器Infinigen Indoors，拓展Infinigen系统至室内场景，含约束布局系统与导出工具，支持具身智能体训练，已开源。
摘要：
我们推出Infinigen Indoors，这是一款基于Blender的照片级真实感室内场景程序化生成器。它以聚焦自然场景的现有Infinigen系统为基础，通过引入包含家具、建筑元素、家电及其他日常物品的多样化程序化室内资产库，将覆盖范围拓展至室内场景。该系统还引入了基于约束的布局系统，包含用于表达场景构成各类约束的领域特定语言，以及生成能最大程度满足约束的场景布局的求解器。我们提供了导出工具，可让生成的3D对象和场景直接用于在Omniverse、Unreal等实时模拟器中训练具身智能体。Infinigen Indoors以BSD许可证开源，代码和视频可访问https://infinigen.org获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
