Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
Keyang Lu, Sifan Zhou, Hongbin Xu, Gang Xu, Zhifei Yang, Yikai Wang, Zhen Xiao, Jieyi Long, Ming Li
Abstract
Realistic 3D city generation is fundamental to a wide range of applications, including virtual reality and digital twins. However, most existing methods rely on training a single diffusion model, which limits their ability to generate personalized and boundless city-scale scenes. In this paper, we present Yo'City, a novel agentic framework that enables user-customized and infinitely expandable 3D city generation by leveraging the reasoning and compositional capabilities of off-the-shelf large models. Specifically, Yo'City first conceptualize the city through a top-down planning strategy that defines a hierarchical “City–District–Grid” structure. The Global Planner determines the overall layout and potential functional districts, while the Local Designer further refines each district with detailed grid-level descriptions. Subsequently, the grid-level 3D generation is achieved through a produce–refine–evaluate isometric image synthesis loop, followed by image-to-3D generation. To simulate continuous city evolution, Yo'City further introduces a user-interactive, relationship-guided expansion mechanism, which performs scene graph–based distance- and semantics-aware layout optimization, ensuring spatially coherent city growth. To comprehensively evaluate our method, we construct a diverse benchmark dataset and design six multi-dimensional metrics that assess generation quality from the perspectives of semantics, geometry, texture, and layout. Extensive experiments demonstrate that Yo'City consistently outperforms existing state-of-the-art methods across all evaluation aspects.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on29
- Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
- SWE-agent: Agent-Computer Interfaces Enable Automated Software EngineeringJohn Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret et al.NeurIPS 2024 · 2,059 citations
- LayoutGPT: Compositional Visual Planning and Generation with Large Language ModelsWeixi Feng, Wanrong Zhu, Tsu-Jui Fu, Varun Jampani et al.NeurIPS 2023 · 462 citations
- ATISS: Autoregressive Transformers for Indoor Scene SynthesisDespoina Paschalidou, Amlan Kar, Maria Shugrina, Karsten Kreis et al.NeurIPS 2021 · 293 citations
- Spatial Mental Modeling from Limited ViewsQineng Wang, Baiqiao Yin, Pingyue Zhang, Jianshu Zhang et al.ICLR 2026 · 92 citations
Related papers
- MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and LayoutsZilong Huang, Jun He, Xiaobin Huang, Ziyi Xiong et al.CVPR 2026 · 5 citations
- Sat2City: 3D City Generation from a Single Satellite Image with Cascaded Latent DiffusionTongyan Hua, Lutao Jiang, Ying-Cong Chen, Wufan ZhaoICCV 2025 · 5 citations
- CitySculpt: 3D City Generation from Satellite Imagery with UV DiffusionXingbo Yao, Xuanmin Wang, Hui XiongACM MM 2025
- WorldGrow: Generating Infinite 3D WorldSikuang Li, Chen Yang, Jiemin Fang, Taoran Yi et al.AAAI 2026 · 10 citations
- InfiniCity: Infinite-Scale City SynthesisChieh Hubert Lin, Hsin-Ying Lee, Willi Menapace, Menglei Chai et al.ICCV 2023 · 86 citations
