Show simple item record

dc.contributor.author
Li, Peizhuo
dc.contributor.author
Aberman, Kfir
dc.contributor.author
Hanocka, Rana
dc.contributor.author
Liu Libin
dc.contributor.author
Sorkine-Hornung, Olga
dc.contributor.author
Chen, Baoquan
dc.date.accessioned
2021-08-05T13:03:50Z
dc.date.available
2021-08-05T03:14:01Z
dc.date.available
2021-08-05T13:03:50Z
dc.date.issued
2021-08
dc.identifier.issn
0730-0301
dc.identifier.issn
1557-7368
dc.identifier.other
10.1145/3450626.3459852
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/499541
dc.description.abstract
Animating a newly designed character using motion capture (mocap) data is a long standing problem in computer animation. A key consideration is the skeletal structure that should correspond to the available mocap data, and the shape deformation in the joint regions, which often requires a tailored, pose-specific refinement. In this work, we develop a neural technique for articulating 3D characters using enveloping with a pre-defined skeletal structure which produces high quality pose dependent deformations. Our framework learns to rig and skin characters with the same articulation structure (e.g., bipeds or quadrupeds), and builds the desired skeleton hierarchy into the network architecture. Furthermore, we propose neural blend shapes - a set of corrective pose-dependent shapes which improve the deformation quality in the joint regions in order to address the notorious artifacts resulting from standard rigging and skinning. Our system estimates neural blend shapes for input meshes with arbitrary connectivity, as well as weighting coefficients which are conditioned on the input joint rotations. Unlike recent deep learning techniques which supervise the network with ground-truth rigging and skinning parameters, our approach does not assume that the training data has a specific underlying deformation model. Instead, during training, the network observes deformed shapes and learns to infer the corresponding rig, skin and blend shapes using indirect supervision. During inference, we demonstrate that our network generalizes to unseen characters with arbitrary mesh connectivity, including unrigged characters built by 3D artists. Conforming to standard skeletal animation models enables direct plug-and-play in standard animation software, as well as game engines.
en_US
dc.language.iso
en
en_US
dc.publisher
Association for Computing Machinery
dc.title
Learning skeletal articulations with neural blend shapes
en_US
dc.type
Journal Article
dc.date.published
2021-07-19
ethz.journal.title
ACM Transactions on Graphics
ethz.journal.volume
40
en_US
ethz.journal.issue
4
en_US
ethz.journal.abbreviated
ACM trans. graph.
ethz.pages.start
130
en_US
ethz.size
15 p.
en_US
ethz.event.location
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, NY
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::02659 - Institut für Visual Computing / Institute for Visual Computing::03911 - Sorkine Hornung, Olga / Sorkine Hornung, Olga
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02659 - Institut für Visual Computing / Institute for Visual Computing::03911 - Sorkine Hornung, Olga / Sorkine Hornung, Olga
ethz.date.deposited
2021-08-05T03:14:12Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-08-05T13:03:56Z
ethz.rosetta.lastUpdated
2024-02-02T14:29:30Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Learning%20skeletal%20articulations%20with%20neural%20blend%20shapes&rft.jtitle=ACM%20Transactions%20on%20Graphics&rft.date=2021-08&rft.volume=40&rft.issue=4&rft.spage=130&rft.issn=0730-0301&1557-7368&rft.au=Li,%20Peizhuo&Aberman,%20Kfir&Hanocka,%20Rana&Liu%20Libin&Sorkine-Hornung,%20Olga&rft.genre=article&rft_id=info:doi/10.1145/3450626.3459852&
 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