COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation

TL;DR

COHO introduces a novel graph-based masked autoencoder for scalable, context-sensitive city-scale urban layout generation, capturing multi-layer semantics and ensuring realism across diverse urban styles.

Contribution

It presents a new graph representation and a masked autoencoder approach for large-scale urban layout generation, addressing prior limitations of rule-based and data-intensive methods.

Findings

Achieves realistic and semantically consistent urban layouts

Effective across 330 US cities with diverse styles

Demonstrates scalability and semantic fidelity in city generation

Abstract

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.