The recent surge in interest in city layout generation underscores its significance in urban planning and smart city development. The task involves procedurally or automatically generating spatial arrangements for urban elements such as roads, buildings, water, and vegetation. Previous methods, whether procedural modeling or deep learning-based approaches like VAEs and GANs, rely on complex priors, expert guidance, or initial layouts, and often lack diversity and interactivity. In this paper, we present CityGen, an end-to-end framework for infinite, diverse, and controllable city layout generation. Our framework introduces an infinite expansion module to extend local layouts to city-scale layouts and a multi-scale refinement module to upsample and refine them. We also designed a user-friendly control scheme, allowing users to guide generation through simple sketching. Additionally, we convert the 2D layout to 3D by synthesizing a height field, facilitating downstream applications. Extensive experiments demonstrate CityGen's state-of-the-art performance across various metrics, making it suitable for a wide range of downstream applications.
View on arXiv@article{deng2025_2312.01508,
title={ CityGen: Infinite and Controllable City Layout Generation },
author={ Jie Deng and Wenhao Chai and Jianshu Guo and Qixuan Huang and Junsheng Huang and Wenhao Hu and Shengyu Hao and Jenq-Neng Hwang and Gaoang Wang },
journal={arXiv preprint arXiv:2312.01508},
year={ 2025 }
}