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

Automated 3D city generation, focusing on road networks and building layouts, is in high demand for applications in urban planning, analysis, and simulations. The surge in deep generative models has facilitated automated design in recent years. However, the lack of high-quality datasets and benchmarks hinders the progress of these data-driven methods in generating city configurations. To fill this gap, this study introduces a multimodal dataset designed for the controllable generation of road networks and building layouts (named RoBus), whose public project repository provides release materials, and constitutes a large-scale resource in the field of generative city design. The RoBus dataset comprises aligned images, graphics, labels, and texts, with 72,400 paired samples that cover around 80,000 km2 globally. Besides utilizing prevalent generative models, we also introduce baseline models that leverage the multimodal features of RoBus. The experiments establish the dataset’s usability while revealing complementary trade-offs rather than uniform superiority. ControlNet obtains the lowest road network FID (20.78), whereas our topology-aware road baseline obtains the highest traffic-convenience score (0.83) at the cost of lower fidelity and diversity. For building layouts, our multimodal baseline reduces FID to 17.42 and building-density Wasserstein distance from 6.12 to 3.37 but produces lower diversity and a higher invalid-sample rate than the strongest comparison methods.