To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation
Not on the map. Why?
Abstract (arXiv)
Text-driven 3D generation has advanced rapidly in creating large-scale outdoor environments and detailed indoor scenes, but these domains are usually synthesized independently, lacking the correspondence required for a coherent urban world. We present HoloWorld, a unified indoor-outdoor urban world generation framework built on a continuously updated cross-scale world context. Initializing from a user description, HoloWorld progressively represents and updates the diverse world information, from city-scale planning to individual buildings, allowing generated interiors to maintain explicit correspondence with their associated exterior buildings. Conditioned on the evolving context and previously generated neighboring blocks, HoloWorld autoregressively generates urban exteriors with consistent spatial organization and visual identity across blocks. The generated exterior representations are further grounded in 3D building instances and footprints, enabling building-specific indoor generation with geometry-constrained layouts and inherited appearance characteristics. To our knowledge, HoloWorld is the first framework to unify indoor and outdoor generation within a coherent 3D urban world. Extensive experiments demonstrate that HoloWorld achieves superior urban exterior generation performance, improving the average AQS score over the SOTA by 7.68% and obtaining the highest average RDR score, while maintaining strong building-level indoor-outdoor correspondence and cross-block continuity within a unified 3D urban world. Our project page: https://huangxb326.github.io/HoloWorld/.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 27 references that are in the map. First posted on arXiv 6 Aug 2026.
Builds on
23 of 27 references.
References · 23
- 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
- 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 268
- 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 200
- 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 166
- 2020SceneFormer: Indoor Scene Generation with Transformerscited by 158
- 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 153
- 2023AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homescited by 82
- 2025Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generationcited by 67
- 2023SceneWiz3D: Towards Text-guided 3D Scene Compositioncited by 54
- 2026SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenescited by 46
- 2024Generative Gaussian Splatting for Unbounded 3D City Generationcited by 44
- 2025SynCity: Training-Free Generation of 3D Worldscited by 31
11 more
- 20243D-SceneDreamer: Text-Driven 3D-Consistent Scene Generationcited by 29
- 2023UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fieldscited by 26
- 2024CityCraft: A Real Crafter for 3D City Generationcited by 26
- 2025WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agentscited by 21
- 2025WorldGen: From Text to Traversable and Interactive 3D Worldscited by 19
- 2025Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objectscited by 11
- 2025Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansioncited by 9
- 2026MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon taskscited by 8
- 2025MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layoutscited by 6
- 2026SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generationcited by 6
- 2026ShellMaker: Language-Guided Exterior Completion under Structural Constraintscited by 2
Built on by
Not cited yet.