Show simple item record

dc.contributor.author
Portenier, Tiziano
dc.contributor.author
Bigdeli, Siavash
dc.contributor.author
Goksel, Orcun
dc.contributor.editor
Larochelle, Hugo
dc.contributor.editor
Ranzato, Marc'Aurelio
dc.contributor.editor
Hadsell, Raia
dc.contributor.editor
Balcan, Maria F.
dc.contributor.editor
Lin, H.
dc.date.accessioned
2021-07-21T08:35:22Z
dc.date.available
2020-12-11T13:02:27Z
dc.date.available
2020-12-11T13:22:15Z
dc.date.available
2021-03-15T09:56:01Z
dc.date.available
2021-07-21T08:35:22Z
dc.date.issued
2021
dc.identifier.isbn
978-1-7138-2954-6
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/456036
dc.identifier.doi
10.3929/ethz-b-000456036
dc.description.abstract
We present a novel texture synthesis framework, enabling the generation of infinite, high-quality 3D textures given a 2D exemplar image. Inspired by recent advances in natural texture synthesis, we train deep neural models to generate textures by non-linearly combining learned noise frequencies. To achieve a highly realistic output conditioned on an exemplar patch, we propose a novel loss function that combines ideas from both style transfer and generative adversarial networks. In particular, we train the synthesis network to match the Gram matrices of deep features from a discriminator network. In addition, we propose two architectural concepts and an extrapolation strategy that significantly improve generalization performance. In particular, we inject both model input and condition into hidden network layers by learning to scale and bias hidden activations. Quantitative and qualitative evaluations on a diverse set of exemplars motivate our design decisions and show that our system performs superior to previous state of the art. Finally, we conduct a user study that confirms the benefits of our framework.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Curran
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.title
GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2020
ethz.book.title
Advances in Neural Information Processing Systems 33
en_US
ethz.pages.start
6994
en_US
ethz.pages.end
7004
en_US
ethz.size
11 p. accepted version; 12 p. supplemental material
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.event
34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020)
en_US
ethz.event.location
Online
en_US
ethz.event.date
December 6-12, 2020
en_US
ethz.notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.publication.place
Red Hook, NY
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::09528 - Göksel, Orçun (SNF-Professur) / Göksel, Orçun (SNF-Professur)
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::09528 - Göksel, Orçun (SNF-Professur) / Göksel, Orçun (SNF-Professur)
en_US
ethz.identifier.url
https://proceedings.neurips.cc/paper/2020/hash/4df5bde009073d3ef60da64d736724d6-Abstract.html
ethz.date.deposited
2020-12-11T13:02:37Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2020-12-11T13:22:27Z
ethz.rosetta.lastUpdated
2020-12-11T13:22:27Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=GramGAN:%20Deep%203D%20Texture%20Synthesis%20From%202D%20Exemplars&rft.date=2021&rft.spage=6994&rft.epage=7004&rft.au=Portenier,%20Tiziano&Bigdeli,%20Siavash&Goksel,%20Orcun&rft.isbn=978-1-7138-2954-6&rft.genre=proceeding&rft.btitle=Advances%20in%20Neural%20Information%20Processing%20Systems%2033
 Search print copy at ETH Library

Files in this item

Thumbnail
Thumbnail

Publication type

Show simple item record