Re-designing cities with conditional adversarial networks

TL;DR

This paper presents a novel conditional GAN framework for urban scene redesign, capable of generating intervention policies, attention maps, and high-resolution images, supported by a new dataset of real urban interventions.

Contribution

It introduces a new GAN-based method for city redesign that produces detailed intervention plans and high-res images, advancing urban planning automation.

Findings

Outperforms existing image-to-image translation methods in urban scene editing.

Successfully generates high-resolution images of urban interventions.

Demonstrates strong performance across various urban scenarios.

Abstract

This paper introduces a conditional generative adversarial network to redesign a street-level image of urban scenes by generating 1) an urban intervention policy, 2) an attention map that localises where intervention is needed, 3) a high-resolution street-level image (1024 X 1024 or 1536 X1536) after implementing the intervention. We also introduce a new dataset that comprises aligned street-level images of before and after urban interventions from real-life scenarios that make this research possible. The introduced method has been trained on different ranges of urban interventions applied to realistic images. The trained model shows strong performance in re-modelling cities, outperforming existing methods that apply image-to-image translation in other domains that is computed in a single GPU. This research opens the door for machine intelligence to play a role in re-thinking and re-designing the different attributes of cities based on adversarial learning, going beyond the mainstream of facial landmarks manipulation or image synthesis from semantic segmentation.