Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation
This work addresses the need for scalable and customizable indoor scene generation for robotics and AI simulation, though it is incremental as it builds upon prior work.
The authors tackled the problem of generating photorealistic indoor scenes for training embodied agents by introducing Infinigen Indoors, a Blender-based procedural generator that expands on an existing system for natural scenes, resulting in a diverse library of indoor assets and a constraint-based arrangement system for scene composition.
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.