Show simple item record

dc.contributor.authorChu, Hang
dc.contributor.authorLi, Daiqing
dc.contributor.authorAcuna, David
dc.contributor.authorKar, Amlan
dc.contributor.authorShugrina, Maria
dc.contributor.authorWei, Xinkai
dc.contributor.authorLiu, Ming-Yu
dc.contributor.authorTorralba, Antonio
dc.contributor.authorFidler, Sanja
dc.date.accessioned2021-05-04T14:20:38Z
dc.date.available2021-05-04T14:20:38Z
dc.date.issued2020-02
dc.date.submitted2019-10
dc.identifier.isbn9781728148038
dc.identifier.issn2380-7504
dc.identifier.urihttps://hdl.handle.net/1721.1/130552
dc.description.abstractWe 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.en_US
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/iccv.2019.00462en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleNeural Turtle Graphics for Modeling City Road Layoutsen_US
dc.typeArticleen_US
dc.identifier.citationChu, 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 IEEEen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.relation.journal2019 IEEE/CVF International Conference on Computer Visionen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2021-04-15T17:18:41Z
dspace.orderedauthorsChu, H; Li, D; Acuna, D; Kar, A; Shugrina, M; Wei, X; Liu, M-Y; Torralba, A; Fidler, Sen_US
dspace.date.submission2021-04-15T17:18:46Z
mit.licenseOPEN_ACCESS_POLICY


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record