Show simple item record

dc.contributor.author
Bühler, Marcel C.
dc.contributor.author
Meka, Abhimitra
dc.contributor.author
Li, Gengyan
dc.contributor.author
Beeler, Thabo
dc.contributor.author
Hilliges, Otmar
dc.date.accessioned
2022-06-30T09:07:30Z
dc.date.available
2021-11-26T16:43:14Z
dc.date.available
2021-11-30T08:06:34Z
dc.date.available
2022-06-21T13:28:55Z
dc.date.available
2022-06-30T09:07:30Z
dc.date.issued
2021
dc.identifier.isbn
978-1-6654-2812-5
en_US
dc.identifier.isbn
978-1-6654-2813-2
en_US
dc.identifier.other
10.1109/ICCV48922.2021.01363
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/517228
dc.description.abstract
Deep generative models can synthesize photorealistic images of human faces with novel identities. However, a key challenge to the wide applicability of such techniques is to provide independent control over semantically meaningful parameters: appearance, head pose, face shape, and facial expressions. In this paper, we propose VariTex - to the best of our knowledge the first method that learns a variational latent feature space of neural face textures, which allows sampling of novel identities. We combine this generative model with a parametric face model and gain explicit control over head pose and facial expressions. To generate complete images of human heads, we propose an additive decoder that adds plausible details such as hair. A novel training scheme enforces a pose-independent latent space and in consequence, allows learning a one-to-many mapping between latent codes and pose-conditioned exterior regions. The resulting method can generate geometrically consistent images of novel identities under fine-grained control over head pose, face shape, and facial expressions. This facilitates a broad range of downstream tasks, like sampling novel identities, changing the head pose, expression transfer, and more.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.subject
Image and video synthesis
en_US
dc.subject
Faces
en_US
dc.subject
Neural generative models
en_US
dc.title
VariTex: Variational Neural Face Textures
en_US
dc.type
Conference Paper
dc.date.published
2022-02-28
ethz.book.title
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
en_US
ethz.pages.start
13870
en_US
ethz.pages.end
13879
en_US
ethz.event
18th International Conference on Computer Vision (ICCV 2021)
en_US
ethz.event.location
Online
ethz.event.date
October 11-17, 2021
en_US
ethz.grant
Optimization-based End-User Design of Interactive Technologies
en_US
ethz.identifier.wos
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02658 - Inst. Intelligente interaktive Systeme / Inst. Intelligent Interactive Systems::03979 - Hilliges, Otmar / Hilliges, Otmar
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02658 - Inst. Intelligente interaktive Systeme / Inst. Intelligent Interactive Systems::03979 - Hilliges, Otmar / Hilliges, Otmar
en_US
ethz.grant.agreementno
717054
ethz.grant.fundername
EC
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.program
H2020
ethz.date.deposited
2021-11-26T16:43:22Z
ethz.source
BATCH
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2022-06-21T13:29:19Z
ethz.rosetta.lastUpdated
2023-02-07T03:54:06Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=VariTex:%20Variational%20Neural%20Face%20Textures&rft.date=2021&rft.spage=13870&rft.epage=13879&rft.au=B%C3%BChler,%20Marcel%20C.&Meka,%20Abhimitra&Li,%20Gengyan&Beeler,%20Thabo&Hilliges,%20Otmar&rft.isbn=978-1-6654-2812-5&978-1-6654-2813-2&rft.genre=proceeding&rft_id=info:doi/10.1109/ICCV48922.2021.01363&rft.btitle=2021%20IEEE/CVF%20International%20Conference%20on%20Computer%20Vision%20(ICCV)
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record