cs.CVAug 6, 2026

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

Authors: Xiaobin HuangZilong HuangYang LuoHongchao FanYiping ChenTing Han

Organizations: 1Sun Yat-sen University · 2Norwegian University of Science and Technology · 1Sun Yat-sen

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.

Explore similar work

CardsList
  1. Map2World: Segment Map Conditioned Text to 3D World Generation

    May 1, 2026Jaeyoung Chung, Suyoung Lee, Jianfeng Xiang +2Unknown Environments

  2. WorldClaw: Agentic 3D Open-World Generation at Scale

    Aug 5, 2026Chunchao Guo, Jinpeng Li, Yang Li +13D Scenes3D World