Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion

TL;DR

Yo'City is a novel framework for personalized, infinitely expandable 3D city scene generation that leverages large models for hierarchical planning, detailed synthesis, and dynamic city evolution, outperforming existing methods.

Contribution

It introduces a hierarchical planning and synthesis approach combined with an interactive expansion mechanism for scalable, personalized 3D city generation using large models.

Findings

Outperforms state-of-the-art methods across multiple metrics.

Enables user-customized, boundless city scene creation.

Provides a comprehensive benchmark and evaluation metrics.

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 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.