於生活情境中窺見世界:統一的室內外城市世界生成
To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation
August 29, 2026
作者: Xiaobin Huang, Zilong Huang, Yang Luo, Hongchao Fan, Yiping Chen, Ting Han
cs.AI
摘要
文本驅動的三維生成技術在創建大規模室外環境與精細室內場景方面已快速發展,然而這些領域通常被獨立合成,缺乏構成一致城市世界所需的對應關係。我們提出 HoloWorld——一個基於持續更新的跨尺度世界上下文所建構的統一室內外城市世界生成框架。HoloWorld 從使用者描述出發,逐步表示並更新從城市尺度規劃到個別建築的多元世界資訊,使生成的室內空間能與其相關的外部建築保持明確對應。在不斷演進的上下文及先前生成的相鄰街區條件下,HoloWorld 以自迴歸方式生成城市外部場景,並在街區之間維持一致的空間組織與視覺特徵。生成的室外表徵進一步以三維建築實例與建築足跡為基礎,從而在幾何約束佈局及繼承的外觀特徵下,實現建築特定之室內生成。據我們所知,HoloWorld 是首個在一致的三維城市世界中統合室內與室外生成的框架。大量實驗表明,HoloWorld 取得了優越的城市外部生成表現,其平均 AQS 分數較目前最佳技術(SOTA)提升 7.68%,並獲得最高平均 RDR 分數,同時在統一的三維城市世界中維持強健的建築層級室內外對應與跨街區連續性。我們的專案頁面:https://huangxb326.github.io/HoloWorld/。
English
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/.