Show simple item record

dc.contributor.author
Song, Liangchen
dc.contributor.author
Chen, Anpei
dc.contributor.author
Li, Zhong
dc.contributor.author
Chen, Zhang
dc.contributor.author
Chen, Lele
dc.contributor.author
Yuan, Junsong
dc.contributor.author
Xu, Yi
dc.contributor.author
Geiger, Andreas
dc.date.accessioned
2023-04-18T08:51:32Z
dc.date.available
2023-04-15T03:38:39Z
dc.date.available
2023-04-18T08:51:32Z
dc.date.issued
2023-05
dc.identifier.issn
1077-2626
dc.identifier.issn
1941-0506
dc.identifier.issn
2160-9306
dc.identifier.other
10.1109/TVCG.2023.3247082
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/608064
dc.description.abstract
Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest. The task is especially appealing when only a few or even single RGB cameras are used for capturing the dynamic scene. To this end, we present an efficient framework capable of fast reconstruction, compact modeling, and streamable rendering. First, we propose to decompose the 4D spatiotemporal space according to temporal characteristics. Points in the 4D space are associated with probabilities of belonging to three categories: static, deforming, and new areas. Each area is represented and regularized by a separate neural field. Second, we propose a hybrid representations based feature streaming scheme for efficiently modeling the neural fields. Our approach, coined NeRFPlayer, is evaluated on dynamic scenes captured by single hand-held cameras and multi-camera arrays, achieving comparable or superior rendering performance in terms of quality and speed comparable to recent state-of-the-art methods, achieving reconstruction in 10 seconds per frame and interactive rendering. Project website: https://bit.ly/nerfplayer.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.subject
Neural rendering
en_US
dc.subject
free-viewpoint video
en_US
dc.subject
immersive video
en_US
dc.subject
NeRF
en_US
dc.title
NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields
en_US
dc.type
Journal Article
dc.date.published
2023-02-22
ethz.journal.title
IEEE Transactions on Visualization and Computer Graphics
ethz.journal.volume
29
en_US
ethz.journal.issue
5
en_US
ethz.journal.abbreviated
IEEE trans. vis. comput. graph.
ethz.pages.start
2732
en_US
ethz.pages.end
2742
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, NY
en_US
ethz.publication.status
published
en_US
ethz.date.deposited
2023-04-15T03:38:41Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2023-04-18T08:51:33Z
ethz.rosetta.lastUpdated
2024-02-02T21:41:42Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=NeRFPlayer:%20A%20Streamable%20Dynamic%20Scene%20Representation%20with%20Decomposed%20Neural%20Radiance%20Fields&rft.jtitle=IEEE%20Transactions%20on%20Visualization%20and%20Computer%20Graphics&rft.date=2023-05&rft.volume=29&rft.issue=5&rft.spage=2732&rft.epage=2742&rft.issn=1077-2626&1941-0506&2160-9306&rft.au=Song,%20Liangchen&Chen,%20Anpei&Li,%20Zhong&Chen,%20Zhang&Chen,%20Lele&rft.genre=article&rft_id=info:doi/10.1109/TVCG.2023.3247082&
 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