Neural 3D Video Synthesis from Multi-view Video

We propose a novel approach for 3D video synthesis that is able to represent multi-view video recordings of a dynamic real-world scene in a compact, yet expressive representation that enables high-quality view synthesis and motion interpolation. Our approach takes the high quality and compactness of...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 5511 - 5521
Hlavní autoři: Li, Tianye, Slavcheva, Mira, Zollhoefer, Michael, Green, Simon, Lassner, Christoph, Kim, Changil, Schmidt, Tanner, Lovegrove, Steven, Goesele, Michael, Newcombe, Richard, Lv, Zhaoyang
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2022
Témata:
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We propose a novel approach for 3D video synthesis that is able to represent multi-view video recordings of a dynamic real-world scene in a compact, yet expressive representation that enables high-quality view synthesis and motion interpolation. Our approach takes the high quality and compactness of static neural radiance fields in a new direction: to a model-free, dynamic setting. At the core of our approach is a novel time-conditioned neural radiance field that represents scene dynamics using a set of compact latent codes. We are able to significantly boost the training speed and perceptual quality of the generated imagery by a novel hierarchical training scheme in combination with ray importance sampling. Our learned representation is highly compact and able to represent a 10 second 30 FPS multi-view video recording by 18 cameras with a model size of only 28MB. We demonstrate that our method can render high-fidelity wide-angle novel views at over 1K resolution, even for complex and dynamic scenes. We perform an extensive qualitative and quantitative evaluation that shows that our approach outperforms the state of the art. Project website: https://neural-3d-video.github.io/.
AbstractList We propose a novel approach for 3D video synthesis that is able to represent multi-view video recordings of a dynamic real-world scene in a compact, yet expressive representation that enables high-quality view synthesis and motion interpolation. Our approach takes the high quality and compactness of static neural radiance fields in a new direction: to a model-free, dynamic setting. At the core of our approach is a novel time-conditioned neural radiance field that represents scene dynamics using a set of compact latent codes. We are able to significantly boost the training speed and perceptual quality of the generated imagery by a novel hierarchical training scheme in combination with ray importance sampling. Our learned representation is highly compact and able to represent a 10 second 30 FPS multi-view video recording by 18 cameras with a model size of only 28MB. We demonstrate that our method can render high-fidelity wide-angle novel views at over 1K resolution, even for complex and dynamic scenes. We perform an extensive qualitative and quantitative evaluation that shows that our approach outperforms the state of the art. Project website: https://neural-3d-video.github.io/.
Author Zollhoefer, Michael
Schmidt, Tanner
Goesele, Michael
Lovegrove, Steven
Green, Simon
Li, Tianye
Slavcheva, Mira
Lv, Zhaoyang
Lassner, Christoph
Newcombe, Richard
Kim, Changil
Author_xml – sequence: 1
  givenname: Tianye
  surname: Li
  fullname: Li, Tianye
  organization: University of Southern,California
– sequence: 2
  givenname: Mira
  surname: Slavcheva
  fullname: Slavcheva, Mira
  organization: Reality Labs Research
– sequence: 3
  givenname: Michael
  surname: Zollhoefer
  fullname: Zollhoefer, Michael
  organization: Reality Labs Research
– sequence: 4
  givenname: Simon
  surname: Green
  fullname: Green, Simon
  organization: Reality Labs Research
– sequence: 5
  givenname: Christoph
  surname: Lassner
  fullname: Lassner, Christoph
  organization: Reality Labs Research
– sequence: 6
  givenname: Changil
  surname: Kim
  fullname: Kim, Changil
  organization: Meta
– sequence: 7
  givenname: Tanner
  surname: Schmidt
  fullname: Schmidt, Tanner
  organization: Reality Labs Research
– sequence: 8
  givenname: Steven
  surname: Lovegrove
  fullname: Lovegrove, Steven
  organization: Reality Labs Research
– sequence: 9
  givenname: Michael
  surname: Goesele
  fullname: Goesele, Michael
  organization: Reality Labs Research
– sequence: 10
  givenname: Richard
  surname: Newcombe
  fullname: Newcombe, Richard
  organization: Reality Labs Research
– sequence: 11
  givenname: Zhaoyang
  surname: Lv
  fullname: Lv, Zhaoyang
  organization: Reality Labs Research
BookMark eNotjstKw0AUQEdRsK39Al3kB5LeO4-bmaXEJ9QHProtk8wNjqSJJKnSv1epq7M4cDhTcdR2LQtxjpAhglsUq6dnI8naTIKUGYDR-kBMkchocprUoZggkErJoTsR82H4AAAlEcnZiVg88Lb3TaIuk1UM3CUvu3Z85yEOSd13m-R-24wx_Yr8vfen4rj2zcDzf87E2_XVa3GbLh9v7oqLZRolqDH1VgWJdU7GVMFom5s8eJJVYHKevf2Do1pqJKxUCWVlqvL3CZT3eZClmomzfTcy8_qzjxvf79bO5tZZp34AQ5lFMg
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52688.2022.00544
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665469463
9781665469463
EISSN 1063-6919
EndPage 5521
ExternalDocumentID 9878989
Genre orig-research
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i203t-a83d21f7655cd548757da62cde69aea8e69a96f24161c3b0bc5cb21103aa7d2b3
IEDL.DBID RIE
ISICitedReferencesCount 177
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000867754205075&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:15:10 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-a83d21f7655cd548757da62cde69aea8e69a96f24161c3b0bc5cb21103aa7d2b3
PageCount 11
ParticipantIDs ieee_primary_9878989
PublicationCentury 2000
PublicationDate 2022-June
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: 2022-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.660716
Snippet We propose a novel approach for 3D video synthesis that is able to represent multi-view video recordings of a dynamic real-world scene in a compact, yet...
SourceID ieee
SourceType Publisher
StartPage 5511
SubjectTerms 3D from multi-view and sensors; Image and video synthesis and generation
Cameras
Dynamics
Heuristic algorithms
Interpolation
Monte Carlo methods
Three-dimensional displays
Training
Title Neural 3D Video Synthesis from Multi-view Video
URI https://ieeexplore.ieee.org/document/9878989
WOSCitedRecordID wos000867754205075&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5q8eCpaiu-ycGjsbvJbh7navEgpfgovZW8CguylW4r-O_N7C4VwYunhOQQkhBmvsl83wDcKBmsYSmnJsJlmkUPgUYrl1BlteI21UHUap-zJzmZqPlcTztwu-PChBDq5LNwh936L9-v3BZDZcOIj7Ha4R7sSSkartYunsIjkhFatey4NNHD0Wz6jGImmMDFUJYzz7JfNVRqEzLu_W_xQxj8cPHIdGdljqATymPotc4jaZ9m1YchymyYd8LvyazwYUVevsro3FVFRZBCQmqmLcWPgGZ-AG_jh9fRI22rIdCCJXxDjeKepUsp8tz5GmdIbwRzPghtglHYaLFkiFgct4l1ubMI77gx0jPLT6BbrspwCoQ5pZa51doIn2krbXSzvGTB5UkQmVZn0Mf9Lz4awYtFu_Xzv4cv4AAPuMmfuoTuZr0NV7DvPjdFtb6ub-kbyp2Rdg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5qFfRUtYpvc_Bo7G6ym8e5WirWUrSW3kpehQXZSrcV_Pcmu0tF8OIpISGEJISZL5nvG4AbwZ1WJKZYebiME-8hYG_lIiy0FFTH0rFS7XMy4MOhmE7lqAG3Gy6Mc64MPnN3oVr-5duFWYenso7HxyHb4RZsp0lCooqttXlRoR7LMClqflwcyU53MnoJciYhhIsEYU4_7FcWldKI9Fr_m34fjn7YeGi0sTMH0HD5IbRq9xHVl7NoQycIbah3RO_RJLNugV6_cu_eFVmBAokElVxbHL4Cqv4jeOs9jLt9XOdDwBmJ6AorQS2J55ylqbEl0uBWMWKsY1I5JUIh2ZwEzGKojrRJjQ4AjyrFLdH0GJr5IncngIgRYp5qKRWzidRce0fLcuJMGjmWSHEK7bD-2UcleTGrl372d_M17PbHz4PZ4HH4dA57YbOraKoLaK6Wa3cJO-ZzlRXLq_LEvgGOk5S9
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Neural+3D+Video+Synthesis+from+Multi-view+Video&rft.au=Li%2C+Tianye&rft.au=Slavcheva%2C+Mira&rft.au=Zollhoefer%2C+Michael&rft.au=Green%2C+Simon&rft.date=2022-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=5511&rft.epage=5521&rft_id=info:doi/10.1109%2FCVPR52688.2022.00544&rft.externalDocID=9878989