Generating Urban Road Networks with Conditional Diffusion Models

The auto-generation of urban roads can greatly improve efficiency and productivity in urban planning and designing. However, it has also raised concerns amongst researchers over the past decade. In this paper, we present an image-based urban road network generation framework using conditional diffusion models. We first trained a diffusion model capable of generating road images with similar characteristics to the ground truth using four context factors. Then, we used the trained model as the generator to synthesize road images conditioned in a geospatial context. Finally, we converted the generated road images into road networks with several post-processes. The experiments conducted in five cities of the United States showed that our model can generate reasonable road networks, maintaining the layouts and styles of real examples. Moreover, our model has the ability to show the obstructive effect of geographic barriers on urban roads. By comparing models with different context factors as input, we find that the model that considers all four factors generally performs the best. The most important factor in guiding the shape of road networks is intersections, implying that the development of urban roads is not only restricted by the natural environment but is more strongly influenced by human design

Diffusion · Econometrics · Physics · Computer Science · Data Management and Algorithms · Mathematics · Traffic control and management · Transportation Planning and Optimization

• Procedural generation as an approach for digital representation of a city

  Open Access•Farshad Shariatpour, Amir Shakibamanesh et al.•Computational Urban Science•2026

  Incluir item

• Advancing urban hub planning

  Xiaodong Xu, Shiqi Zhou et al.

  Incluir item

• Elementary processes governing the evolution of road networks

  Open Access•Emanuele Strano, Vincenzo Nicosia et al.•Scientific Reports•2012

  Incluir item

• Generative urban design

  Open Access•Feifeng Jiang, Jun Ma et al.•Progress in Planning•2024

  Incluir item

• Incorporating Planning Intelligence into Deep Learning

  Zhou Fang, Ying Jin et al.•Journal of Urban Technology•2021

  Incluir item

• Road expansion and persistence in forests of the Congo Basin

  Open Access•Fritz Kleinschroth, Nadine Laporte et al.•Nature Sustainability•2019

  Incluir item

• Urban spatial order

  Open Access•Geoff Boeing•Applied Network Science•2019

  Incluir item