RoBus: A Multimodal Dataset for Controllable Road Networks and Building Layouts Generation

TL;DR

This paper introduces RoBus, a large multimodal dataset for controllable generation of city road networks and building layouts, enabling more practical urban design with deep learning models.

Contribution

The paper presents RoBus, the first large-scale open-source dataset for city generation, including evaluation metrics and baseline models that incorporate urban characteristics.

Findings

RoBus contains 72,400 paired samples covering 80,000 km^2.

Validated effectiveness of dataset against existing methods.

Enhanced generation models with urban features like road orientation and density.

Abstract

Automated 3D city generation, focusing on road networks and building layouts, is in high demand for applications in urban design, multimedia games and autonomous driving simulations. The surge of generative AI facilitates designing city layouts based on deep learning models. However, the lack of high-quality datasets and benchmarks hinders the progress of these data-driven methods in generating road networks and building layouts. Furthermore, few studies consider urban characteristics, which generally take graphics as analysis objects and are crucial for practical applications, to control the generative process. To alleviate these problems, we introduce a multimodal dataset with accompanying evaluation metrics for controllable generation of Road networks and Building layouts (RoBus), which is the first and largest open-source dataset in city generation so far. RoBus dataset is formatted as images, graphics and texts, with $72,400$ paired samples that cover around $80,000km^2$ globally. We analyze the RoBus dataset statistically and validate the effectiveness against existing road networks and building layouts generation methods. Additionally, we design new baselines that incorporate urban characteristics, such as road orientation and building density, in the process of generating road networks and building layouts using the RoBus dataset, enhancing the practicality of automated urban design. The RoBus dataset and related codes are published at https://github.com/tourlics/RoBus_Dataset.