🤖 AI Summary
Generating high-quality urban street layouts that jointly model natural (e.g., terrain, hydrology) and socioeconomic (e.g., population, POIs, road density) factors remains challenging.
Method: This paper proposes a conditional adversarial learning framework that jointly encodes multi-source natural and socioeconomic features into a conditional GAN architecture. A lightweight graph extraction module enables end-to-end mapping from synthesized images to topologically consistent street graphs. The method integrates autoencoder-based feature fusion with image-to-graph post-processing.
Contribution/Results: The generated layouts achieve strong fidelity in both visual appearance and graph-theoretic metrics—including connectivity, degree distribution, and betweenness—closely matching real-world street networks. Experiments demonstrate semantic controllability and high-fidelity virtual urban scene generation: FID improves by 23.6% and graph structural similarity increases by 19.4% across multiple city datasets.
📝 Abstract
The demand for high-quality city street layouts has persisted for an extended period presenting notable challenges. Conventional methods are yet to effectively address the integration of both natural and socioeconomic factors in this complex task. In this study, we propose a novel conditional adversarial learning-based method for city street layout generation from natural and socioeconomic conditions. Specifically, we design an image synthesis module that leverages an autoencoder to fuse a set of natural and socioeconomic data for a given region of interest into a feature map, and then employs a conditional generative adversarial network trained on real-world data to synthesize street layout images from the feature map. Afterward, a graph extraction module converts each synthesized image to the corresponding high-quality street layout graph. Experiments and evaluations suggest that the proposed method produces diverse city street layouts that closely resemble their real-world counterparts both visually and structurally. This capability can facilitate the creation of high-quality virtual city scenes.
