COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation
This addresses the need for scalable urban layout generation in fields like urban planning, offering a novel method that improves over prior approaches by incorporating context sensitivity.
The paper tackles the problem of generating large-scale urban layouts by introducing a context-sensitive, graph-based masked autoencoder that achieves good realism, semantic consistency, and correctness across 330 US cities.
The generation of large-scale urban layouts has garnered substantial interest across various disciplines. Prior methods have utilized procedural generation requiring manual rule coding or deep learning needing abundant data. However, prior approaches have not considered the context-sensitive nature of urban layout generation. Our approach addresses this gap by leveraging a canonical graph representation for the entire city, which facilitates scalability and captures the multi-layer semantics inherent in urban layouts. We introduce a novel graph-based masked autoencoder (GMAE) for city-scale urban layout generation. The method encodes attributed buildings, city blocks, communities and cities into a unified graph structure, enabling self-supervised masked training for graph autoencoder. Additionally, we employ scheduled iterative sampling for 2.5D layout generation, prioritizing the generation of important city blocks and buildings. Our approach achieves good realism, semantic consistency, and correctness across the heterogeneous urban styles in 330 US cities. Codes and datasets are released at https://github.com/Arking1995/COHO.