Show simple item record

dc.contributor.authorKelly, Tom
dc.contributor.authorGuerrero, Paul
dc.contributor.authorSteed, Anthony
dc.contributor.authorWonka, Peter
dc.contributor.authorMitra, Niloy J.
dc.date.accessioned2019-08-06T12:02:25Z
dc.date.available2019-08-06T12:02:25Z
dc.date.issued2018-11-28
dc.identifier.citationKelly, T., Guerrero, P., Steed, A., Wonka, P., & Mitra, N. J. (2018). FrankenGAN. ACM Transactions on Graphics, 37(6), 1–14. doi:10.1145/3272127.3275065
dc.identifier.doi10.1145/3272127.3275065
dc.identifier.urihttp://hdl.handle.net/10754/656365
dc.description.abstractCoarse building mass models are now routinely generated at scales ranging from individual buildings to whole cities. Such models can be abstracted from raw measurements, generated procedurally, or created manually. However, these models typically lack any meaningful geometric or texture details, making them unsuitable for direct display. We introduce the problem of automatically and realistically decorating such models by adding semantically consistent geometric details and textures. Building on the recent success of generative adversarial networks (GANs), we propose FrankenGAN, a cascade of GANs that creates plausible details across multiple scales over large neighborhoods. The various GANs are synchronized to produce consistent style distributions over buildings and neighborhoods.We provide the user with direct control over the variability of the output. We allow him/her to interactively specify the style via images and manipulate style-adapted sliders to control style variability. We test our system on several large-scale examples. The generated outputs are qualitatively evaluated via a set of perceptual studies and are found to be realistic, semantically plausible, and consistent in style.
dc.description.sponsorshipThis project was supported by an ERC Starting Grant (SmartGeometry StG-2013-335373), KAUST-UCL Grant (OSR-2015-CCF-2533), ERC PoC Grant (SemanticCity), the KAUST Office of Sponsored Research (OSR-CRG2017-3426), Open3D Project (EPSRC Grant EP/M013685/1), and a Google Faculty Award (UrbanPlan).
dc.publisherAssociation for Computing Machinery (ACM)
dc.relation.urlhttp://dl.acm.org/citation.cfm?doid=3272127.3275065
dc.rights© ACM, 2018. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM Transactions on Graphics, {[Volume], [Issue], (2018-11-01)} http://doi.acm.org/10.1145/3272127.3275065
dc.titleFrankenGAN: Guided detail synthesis for building mass models using style-Synchonized Gans
dc.typeArticle
dc.contributor.departmentComputer Science Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journalACM Transactions on Graphics
dc.eprint.versionPost-print
dc.contributor.institutionUniversity College London
dc.contributor.institutionUniversity of Leeds
kaust.personWonka, Peter
kaust.grant.numberOSR-2015-CCF-2533
kaust.grant.numberOSR-CRG2017-3426
kaust.acknowledged.supportUnitKAUST Office of Sponsored Research
dc.date.published-online2018-11-28
dc.date.published-print2018-12-04


This item appears in the following Collection(s)

Show simple item record