To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation

2026-08-06

AI Summary

Existing text-driven 3D generation methods struggle to establish consistent correspondences between indoor and outdoor scenes, hindering the creation of coherent city-scale environments. To address this limitation, this work proposes HoloWorld, a novel framework that achieves the first unified, autoregressive indoor-outdoor 3D generation within a single urban context. By integrating cross-scale world context modeling, building instance and footprint constraints, geometric layout optimization, and appearance feature inheritance, HoloWorld ensures both intra-building consistency and inter-block continuity. Experimental results demonstrate that the proposed method surpasses the current state of the art by 7.68% on the AQS metric for urban appearance generation, achieves the highest RDR score, and significantly enhances semantic and spatial alignment between indoor and outdoor spaces.

Abstract

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.

Problem

• indoor-outdoor correspondence
• urban world generation
• 3D scene generation
• text-to-3D
• coherent urban modeling

Innovation

• unified indoor-outdoor generation
• cross-scale world context
• autoregressive urban modeling
• geometry-constrained indoor layout
• 3D urban world coherence