Neural Turtle Graphics for Modeling City Road Layouts
Name
1910.02055.pdf
Description
Accepted version
Size
8.69 MB
Format
Adobe PDF
Checksum (MD5)
35e9c599d9fd82d577cef3fc3acbea83
Author(s)
Chu, Hang
Li, Daiqing
Acuna, David
Kar, Amlan
Shugrina, Maria
Wei, Xinkai
Liu, Ming-Yu
Torralba, Antonio
Fidler, Sanja
Date Issued
February 2020
Journal
2019 IEEE/CVF International Conference on Computer Vision
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Chu, Hang et al. "Neural Turtle Graphics for Modeling City Road Layouts." 2019 IEEE/CVF International Conference on Computer Vision, October-November 2019, Seoul, South Korea, Institute of Electrical and Electronics Engineers, February 2020. © 2019 IEEE
Version
Author's final manuscript
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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/iccv.2019.00462
