Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation

2024/06/17 by Alexander Raistrick, Lingjie Mei, Raistrick, Alexander +21 · 34 citations
Computer Science · Earth and Planetary Sciences · #3D Surveying and Cultural Heritage #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2406.11824

openalex publication_date 2024/06/17 · openalex created_date 2024/06/19 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement
• Particulate: Feed-Forward 3D Object Articulation
• Lighting in Motion: Spatiotemporal HDR Lighting Estimation
• RoomPilot: Controllable Indoor Scene Synthesis via Multimodal Semantic Parsing
• MarketGen: A Scalable Simulation Platform with Auto-Generated Embodied Supermarket Environments
• InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity
• RAISECity: A Multimodal Agent Framework for Reality-Aligned 3D World Generation at City-Scale
• WorldGen: From Text to Traversable and Interactive 3D Worlds
• On 10x Better Scalability: KV Stores Scale Up KV Cache
• Room Envelopes: A Synthetic Dataset for Indoor Layout Reconstruction from Images
• Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulation
• WildShadowRemover: In-the-Wild Video Shadow Removal via Detail-Preserving Video Diffusion Models
• PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement
• Demeter: A Parametric Model of Crop Plant Morphology from the Real World
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
• Toward A Better Understanding of Monocular Depth Evaluation
• A Generalizable Light Transport 3D Embedding for Global Illumination
• Trace Anything: Representing Any Video in 4D via Trajectory Fields
• From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries
• 3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG
• Text-to-Scene with Large Reasoning Models
• NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding
• M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generation
• ControlEvents: Controllable Synthesis of Event Camera Datawith Foundational Prior from Image Diffusion Models
• SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
• Generating Human-AI Collaborative Design Sequence for 3D Assets via Differentiable Operation Graph
• HLG: Comprehensive 3D Room Construction via Hierarchical Layout Generation
• Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training
• SPATIALGEN: Layout-guided 3D Indoor Scene Generation
• InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
• HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction
• MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
• Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering
• HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels

Related

• Infinite Photorealistic Worlds using Procedural Generation
• SceneCraft: Layout-Guided 3D Scene Generation
• VRKitchen2.0-IndoorKit: A Tutorial for Augmented Indoor Scene Building in Omniverse
• Style-Consistent 3D Indoor Scene Synthesis with Decoupled Objects
• Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting