Neural Turtle Graphics for Modeling City Road Layouts

Hang Chu, Daiqing Li, David Acuna, Amlan Kar, Maria Shugrina, Xinkai Wei, Ming-Yu Liu, Antonio Torralba, Sanja Fidler; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 4522-4530

Abstract


We propose Neural Turtle Graphics (NTG), a novel generative model for spatial graphs, and demonstrate its applications in modeling city road layouts. Specifically, we represent the road layout using a graph where nodes in the graph represent control points and edges in the graph represents road segments. NTG is a sequential generative model parameterized by a neural network. It iteratively generates a new node and an edge connecting to an existing node conditioned on the current graph. We train NTG on Open Street Map data and show it outperforms existing approaches using a set of diverse performance metrics. Moreover, our method allows users to control styles of generated road layouts mimicking existing cities as well as to sketch a part of the city road layout to be synthesized. In addition to synthesis, the proposed NTG finds uses in an analytical task of aerial road parsing. Experimental results show that it achieves state-of-the-art performance on the SpaceNet dataset.

Related Material


[pdf] [supp] [video]
[bibtex]
@InProceedings{Chu_2019_ICCV,
author = {Chu, Hang and Li, Daiqing and Acuna, David and Kar, Amlan and Shugrina, Maria and Wei, Xinkai and Liu, Ming-Yu and Torralba, Antonio and Fidler, Sanja},
title = {Neural Turtle Graphics for Modeling City Road Layouts},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}