Large-Scale Auto-Regressive Modeling Of Street Networks
This work addresses the challenge of scalable and diverse road layout generation for urban planning and simulation, representing an incremental improvement over existing methods.
The paper tackles the problem of generating large-scale, high-quality street networks, achieving the creation of traversable graphs covering over 400 square kilometers. It uses a transformer-based generative method trained on OpenStreetMap data and compares favorably to state-of-the-art approaches.
We present a novel generative method for the creation of city-scale road layouts. While the output of recent methods is limited in both size of the covered area and diversity, our framework produces large traversable graphs of high quality consisting of vertices and edges representing complete street networks covering 400 square kilometers or more. While our framework can process general 2D embedded graphs, we focus on street networks due to the wide availability of training data. Our generative framework consists of a transformer decoder that is used in a sliding window manner to predict a field of indices, with each index encoding a representation of the local neighborhood. The semantics of each index is determined by a dictionary of context vectors. The index field is then input to a decoder to compute the street graph. Using data from OpenStreetMap, we train our system on whole cities and even across large countries such as the US, and finally compare it to the state of the art.