GANs for Urban Design
This provides architects and urban planners with a flexible analytical and design tool for adapting to city-specific urban forms, though it is incremental as it applies existing GAN methods to a new domain.
The paper tackles the problem of urban block design by applying Generative Adversarial Networks to learn morphological characteristics from existing urban contexts, achieving results that enable style translation between cities like Milan and Amsterdam through quantitative and qualitative evaluation.
Development and diffusion of machine learning and big data tools provide a new tool for architects and urban planners that could be used as analytical or design instruments. The topic investigated in this paper is the application of Generative Adversarial Networks to the design of an urban block. The research presents a flexible model able to adapt to the morphological characteristics of a city. This method does not define explicitly any of the parameters of an urban block typical for a city, the algorithm learns them from the existing urban context. This approach has been applied to the cities with different morphology: Milan, Amsterdam, Tallinn, Turin, and Bengaluru in order to see the performance of the model and the possibility of style translation between different cities. The data are gathered from Openstreetmap and Open Data portals of the cities. This research presents the results of the experiments and their quantitative and qualitative evaluation.