Papers
arxiv:2602.05362

Imagine a City: CityGenAgent for Procedural 3D City Generation

Published on Feb 27
Authors:
,
,
,
,
,
,
,
,

Abstract

CityGenAgent enables high-fidelity 3D city generation through natural language input by combining supervised fine-tuning and reinforcement learning with spatial and visual consistency rewards.

AI-generated summary

The automated generation of interactive 3D cities is a critical challenge with broad applications in autonomous driving, virtual reality, and embodied intelligence. While recent advances in generative models and procedural techniques have improved the realism of city generation, existing methods often struggle with high-fidelity asset creation, controllability, and manipulation. In this work, we introduce CityGenAgent, a natural language-driven framework for hierarchical procedural generation of high-quality 3D cities. Our approach decomposes city generation into two interpretable components, Block Program and Building Program. To ensure structural correctness and semantic alignment, we adopt a two-stage learning strategy: (1) Supervised Fine-Tuning (SFT). We train BlockGen and BuildingGen to generate valid programs that adhere to schema constraints, including non-self-intersecting polygons and complete fields; (2) Reinforcement Learning (RL). We design Spatial Alignment Reward to enhance spatial reasoning ability and Visual Consistency Reward to bridge the gap between textual descriptions and the visual modality. Benefiting from the programs and the models' generalization, CityGenAgent supports natural language editing and manipulation. Comprehensive evaluations demonstrate superior semantic alignment, visual quality, and controllability compared to existing methods, establishing a robust foundation for scalable 3D city generation.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2602.05362
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2602.05362 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2602.05362 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2602.05362 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.