Guardado en:
Detalles Bibliográficos
Autores principales: Lu, Keyang, Zhou, Sifan, Xu, Hongbin, Xu, Gang, Yang, Zhifei, Wang, Yikai, Xiao, Zhen, Long, Jieyi, Li, Ming
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.18734
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911494836322304
author Lu, Keyang
Zhou, Sifan
Xu, Hongbin
Xu, Gang
Yang, Zhifei
Wang, Yikai
Xiao, Zhen
Long, Jieyi
Li, Ming
author_facet Lu, Keyang
Zhou, Sifan
Xu, Hongbin
Xu, Gang
Yang, Zhifei
Wang, Yikai
Xiao, Zhen
Long, Jieyi
Li, Ming
contents 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 conceptualizes 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18734
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
Lu, Keyang
Zhou, Sifan
Xu, Hongbin
Xu, Gang
Yang, Zhifei
Wang, Yikai
Xiao, Zhen
Long, Jieyi
Li, Ming
Computer Vision and Pattern Recognition
Artificial Intelligence
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 conceptualizes 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.
title Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.18734