Stylizing 3D Scene via Implicit Representation and HyperNetwork

In this work, we aim to address the 3D scene stylization problem - generating stylized images of the scene at arbitrary novel view angles. A straightforward solution is to combine existing novel view synthesis and image/video style transfer approaches, which often leads to blurry results or inconsis...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / IEEE Workshop on Applications of Computer Vision pp. 215 - 224
Main Authors: Chiang, Pei-Ze, Tsai, Meng-Shiun, Tseng, Hung-Yu, Lai, Wei-Sheng, Chiu, Wei-Chen
Format: Conference Proceeding
Language:English
Published: IEEE 01.01.2022
Subjects:
ISSN:2642-9381
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In this work, we aim to address the 3D scene stylization problem - generating stylized images of the scene at arbitrary novel view angles. A straightforward solution is to combine existing novel view synthesis and image/video style transfer approaches, which often leads to blurry results or inconsistent appearance. Inspired by the high-quality results of the neural radiance fields (NeRF) method, we propose a joint framework to directly render novel views with the desired style. Our framework consists of two components: an implicit representation of the 3D scene with the neural radiance fields model, and a hypernetwork to transfer the style information into the scene representation. To alleviate the training difficulties and memory burden, we propose a two-stage training procedure and a patch sub-sampling approach to optimize the style and content losses with the neural radiance fields model. After optimization, our model is able to render consistent novel views at arbitrary view angles with arbitrary style. Both quantitative evaluation and human subject study have demonstrated that the proposed method generates faithful stylization results with consistent appearance across different views.
AbstractList In this work, we aim to address the 3D scene stylization problem - generating stylized images of the scene at arbitrary novel view angles. A straightforward solution is to combine existing novel view synthesis and image/video style transfer approaches, which often leads to blurry results or inconsistent appearance. Inspired by the high-quality results of the neural radiance fields (NeRF) method, we propose a joint framework to directly render novel views with the desired style. Our framework consists of two components: an implicit representation of the 3D scene with the neural radiance fields model, and a hypernetwork to transfer the style information into the scene representation. To alleviate the training difficulties and memory burden, we propose a two-stage training procedure and a patch sub-sampling approach to optimize the style and content losses with the neural radiance fields model. After optimization, our model is able to render consistent novel views at arbitrary view angles with arbitrary style. Both quantitative evaluation and human subject study have demonstrated that the proposed method generates faithful stylization results with consistent appearance across different views.
Author Tsai, Meng-Shiun
Lai, Wei-Sheng
Chiu, Wei-Chen
Chiang, Pei-Ze
Tseng, Hung-Yu
Author_xml – sequence: 1
  givenname: Pei-Ze
  surname: Chiang
  fullname: Chiang, Pei-Ze
  organization: National Yang Ming Chiao Tung University,Taiwan
– sequence: 2
  givenname: Meng-Shiun
  surname: Tsai
  fullname: Tsai, Meng-Shiun
  organization: National Yang Ming Chiao Tung University,Taiwan
– sequence: 3
  givenname: Hung-Yu
  surname: Tseng
  fullname: Tseng, Hung-Yu
  organization: University of California,Merced
– sequence: 4
  givenname: Wei-Sheng
  surname: Lai
  fullname: Lai, Wei-Sheng
  organization: University of California,Merced
– sequence: 5
  givenname: Wei-Chen
  surname: Chiu
  fullname: Chiu, Wei-Chen
  organization: National Yang Ming Chiao Tung University,Taiwan
BookMark eNotjl1LwzAUQKMouE1_gT7kD3Tee7MkzZOMOd1gKDg_Hkea3kp0S0tblPnrHejTgfNwOENxkurEQlwhjBHBXb9NZ68aJzofExCNAYDckRiiMXoCDjUciwGZCWVO5Xgmhl33AaAcOjUQN-t-v40_Mb1LdSvXgRPLr-jlctdsY4i9fOKm5Y5T7_tYJ-lTKRf7htsH7r_r9vNcnFZ-2_HFP0fi5W7-PFtkq8f75Wy6yiKB6rPApig0ayATrCVboYGD0h4pt-GwXRKHErGybMhYdrbyqDi3ZSiLwgQ1Epd_3cjMm6aNO9_uN86CBUPqF0YBSzI
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/WACV51458.2022.00029
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 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 1665409150
9781665409155
EISSN 2642-9381
EndPage 224
ExternalDocumentID 9707062
Genre orig-research
GroupedDBID 29G
29O
6IE
6IF
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i203t-ce6bb5e5026c7727f160e6b5a1287c202d2ecd11f7e6267e97fa13e87dcdbb6c3
IEDL.DBID RIE
ISICitedReferencesCount 74
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000800471200022&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 02:49:39 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-ce6bb5e5026c7727f160e6b5a1287c202d2ecd11f7e6267e97fa13e87dcdbb6c3
PageCount 10
ParticipantIDs ieee_primary_9707062
PublicationCentury 2000
PublicationDate 2022-Jan.
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-Jan.
PublicationDecade 2020
PublicationTitle Proceedings / IEEE Workshop on Applications of Computer Vision
PublicationTitleAbbrev WACV
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0039193
Score 2.559946
Snippet In this work, we aim to address the 3D scene stylization problem - generating stylized images of the scene at arbitrary novel view angles. A straightforward...
SourceID ieee
SourceType Publisher
StartPage 215
SubjectTerms 3D Computer Vision Neural rendering
Computer vision
Optimization
Prediction algorithms
Predictive models
Solid modeling
Three-dimensional displays
Training
Title Stylizing 3D Scene via Implicit Representation and HyperNetwork
URI https://ieeexplore.ieee.org/document/9707062
WOSCitedRecordID wos000800471200022&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/eLvHCXMwlV3PS8MwFA5zePA0dRN_k4NH45Z2aZqjTMcEGUN07jbS5AUK0snWDfSv9yWt04MXb-VRKH1N3_vey_e9EHIVJ85kOhUM05NgfccVU9YkzDcbnN_2cUGVNn2U43E6m6lJg1xvtTAAEMhncOMvw16-XZi1b5V1lcQF6gPujpSy0mp9R91YIRKppXG8p7qvt4MpYgHh2VtRmMnpQeSvA1RC_hi2_vfkfdL5EeLRyTbFHJAGFIekVSNHWv-XqzZC7vLjLf_Ee2h8h3YMYHSTa_oQ-OJ5SZ8C4bXWGRVUF5aOsAJdjisWeIe8DO-fByNWH43A8qgXl8xAkmUCBFZQBvGxdDzpoUloTDfS4CvbCIzl3EnAikWCkk7zGFJpjc2yxMRHpFksCjgmVOk-Ty0IcFiZpTLSKoHUj2HrW0RTEJ-QtvfH_L2afjGvXXH6t_mM7HmHV02Kc9Isl2u4ILtmU-ar5WX4ZF8QJpcq
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwEA5jCvo0dRN_mwcfrVvapmkeZSobzjFkzr2NNrlAQTrZuoH-9V7SOn3wxbdyFEqv6d13l--7EHIVREalScw9TE_cCw2TntQq8myzwdhtH-NUaZOBGA7j6VSOauR6o4UBAEc-gxt76fby9VytbKusLQUuUBtwt3gY-qxUa33H3UAiFqnEcawj26-33QmiAW75W76bymlh5K8jVFwGeWj879l7pPUjxaOjTZLZJzXID0ijwo60-jOXTQTdxcdb9on30OAO7RjC6DpLaN8xxrOCPjvKa6U0ymmSa9rDGnQxLHngLfLycD_u9rzqcAQv8ztB4SmI0pQDxxpKIUIWhkUdNPEEE45Q-MraB6UZMwKwZhEghUlYALHQSqdppIJDUs_nORwRKpOQxRo4GKzNYuEnMoLYDmILNeIpCI5J0_pj9l7Ov5hVrjj523xJdnrjp8Fs0B8-npJd6_yyZXFG6sViBedkW62LbLm4cJ_vCx4lmnE
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+%2F+IEEE+Workshop+on+Applications+of+Computer+Vision&rft.atitle=Stylizing+3D+Scene+via+Implicit+Representation+and+HyperNetwork&rft.au=Chiang%2C+Pei-Ze&rft.au=Tsai%2C+Meng-Shiun&rft.au=Tseng%2C+Hung-Yu&rft.au=Lai%2C+Wei-Sheng&rft.date=2022-01-01&rft.pub=IEEE&rft.eissn=2642-9381&rft.spage=215&rft.epage=224&rft_id=info:doi/10.1109%2FWACV51458.2022.00029&rft.externalDocID=9707062