gDNA: Towards Generative Detailed Human Avatars
dc.contributor.author
Xu, Chen
dc.contributor.author
Jiang, Tianjian
dc.contributor.author
Song, Jie
dc.contributor.author
Yang, Jinlong
dc.contributor.author
Black, Michael J.
dc.contributor.author
Geiger, Andreas
dc.contributor.author
Hilliges, Otmar
dc.date.accessioned
2022-12-12T17:02:03Z
dc.date.available
2022-12-12T16:28:49Z
dc.date.available
2022-12-12T17:02:03Z
dc.date.issued
2022
dc.identifier.isbn
978-1-6654-6946-3
en_US
dc.identifier.isbn
978-1-6654-6947-0
en_US
dc.identifier.other
10.1109/CVPR52688.2022.01978
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/586468
dc.identifier.doi
10.3929/ethz-b-000586468
dc.description.abstract
To make 3D human avatars widely available, we must be able to generate a variety of 3D virtual humans with varied identities and shapes in arbitrary poses. This task is chal-lenging due to the diversity of clothed body shapes, their complex articulations, and the resulting rich, yet stochas-tic geometric detail in clothing. Hence, current methods that represent 3D people do not provide a full generative model of people in clothing. In this paper, we propose a novel method that learns to generate detailed 3D shapes of people in a variety of garments with corresponding skin-ning weights. Specifically, we devise a multi-subject forward skinning module that is learned from only a few posed, unrigged scans per subject. To capture the stochastic nature of high-frequency details in garments, we leverage an adversarial loss formulation that encourages the model to capture the underlying statistics. We provide empirical evi-dence that this leads to realistic generation of local details such as wrinkles. We show that our model is able to gen-erate natural human avatars wearing diverse and detailed clothing. Furthermore, we show that our method can be used on the task of fitting human models to raw scans, out-performing the previous state-of-the-art.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Face and gestures
en_US
dc.title
gDNA: Towards Generative Detailed Human Avatars
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2022-09-27
ethz.book.title
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
en_US
ethz.pages.start
20395
en_US
ethz.pages.end
20405
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.event
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)
en_US
ethz.event.location
New Orleans, LA, USA
en_US
ethz.event.date
June 18-24, 2022
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.date.deposited
2022-12-12T16:28:49Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2022-12-12T17:02:04Z
ethz.rosetta.lastUpdated
2023-02-07T08:43:09Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=gDNA:%20Towards%20Generative%20Detailed%20Human%20Avatars&rft.date=2022&rft.spage=20395&rft.epage=20405&rft.au=Xu,%20Chen&Jiang,%20Tianjian&Song,%20Jie&Yang,%20Jinlong&Black,%20Michael%20J.&rft.isbn=978-1-6654-6946-3&978-1-6654-6947-0&rft.genre=proceeding&rft_id=info:doi/10.1109/CVPR52688.2022.01978&rft.btitle=2022%20IEEE/CVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20(CVPR)
Files in this item
Publication type
-
Conference Paper [35220]