StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this li...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition S. 8789 - 8797
Hauptverfasser: Choi, Yunjey, Choi, Minje, Kim, Munyoung, Ha, Jung-Woo, Kim, Sunghun, Choo, Jaegul
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2018
Schlagworte:
Gallium nitride
Generative adversarial networks
Generators
Hair
Image reconstruction
Task analysis
Training
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks.
AbstractList Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks.
Author Choi, Yunjey
Choi, Minje
Kim, Sunghun
Ha, Jung-Woo
Choo, Jaegul
Kim, Munyoung
Author_xml – sequence: 1
  givenname: Yunjey
  surname: Choi
  fullname: Choi, Yunjey
– sequence: 2
  givenname: Minje
  surname: Choi
  fullname: Choi, Minje
– sequence: 3
  givenname: Munyoung
  surname: Kim
  fullname: Kim, Munyoung
– sequence: 4
  givenname: Jung-Woo
  surname: Ha
  fullname: Ha, Jung-Woo
– sequence: 5
  givenname: Sunghun
  surname: Kim
  fullname: Kim, Sunghun
– sequence: 6
  givenname: Jaegul
  surname: Choo
  fullname: Choo, Jaegul
BookMark eNotzM1OAjEUQOFqNFGRtQs3fYFib__rjhBFEkSj4MqElOkdUx06pjNifHuNujpn9Z2Qg9xmJOQM-AiA-4vJ0_3DSHBwI849mD0y9NaBls4YJbjfJ8fAjWTGgz8iw6575ZwL46RT-pg8P_ahTMeLS7rKqU4Y6RQzltCnHdJx3GHpQkmhoQvsP9vy1tG6LfT2o-kTi-02pExn2_CCrG_Z79BlCblrfoA2n5LDOjQdDv87IKvrq-Xkhs3vprPJeM4SWN0zqZREBWis1VaICFbWXlUhoq4sNxowglCbYKSRla1lJZSOm42vbFDGcS4H5PzPTYi4fi9pG8rX2mnrOSj5DbdjVNU
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2018.00916
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 9781538664209
1538664208
EISSN 1063-6919
EndPage 8797
ExternalDocumentID 8579014
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-i175t-3443e41e6775722d173f94cade5c70651ed124ba6363c7f3c245dbb9c7a468003
IEDL.DBID RIE
ISICitedReferencesCount 2817
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457843608099&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 02:52:16 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-3443e41e6775722d173f94cade5c70651ed124ba6363c7f3c245dbb9c7a468003
PageCount 9
ParticipantIDs ieee_primary_8579014
PublicationCentury 2000
PublicationDate 2018-Jun
PublicationDateYYYYMMDD 2018-06-01
PublicationDate_xml – month: 06
  year: 2018
  text: 2018-Jun
PublicationDecade 2010
PublicationTitle 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
PublicationTitleAbbrev CVPR
PublicationYear 2018
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002683845
ssj0003211698
Score 2.643942
Snippet Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and...
SourceID ieee
SourceType Publisher
StartPage 8789
SubjectTerms Gallium nitride
Generative adversarial networks
Generators
Hair
Image reconstruction
Task analysis
Training
Title StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation
URI https://ieeexplore.ieee.org/document/8579014
WOSCitedRecordID wos000457843608099&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/eLvHCXMwlV07T8MwED61FQMTjxbxlgdGTOtHcjEbqiggoahCgDogVYntSB3aoCbl92M7UWFgYYmceInuYt8X33f3AVxFVhmWS0ElzxJ3MZqqPOKUy5yhc7NmNqiWPGOaJrOZmnbgelsLY60N5DN744chl29KvfFHZcMkQp_160IXEZtare15Co8TkbQZMn8v3J9NrJK2mw8bqeH4ffriuVyePKm8vvkvOZUQTSZ7_3uPfRj8lOWR6TbgHEDHrg5hr8WRpF2lVR8-HIJcP9ylt8QhysLPNc2l_c5GggJzlfnvjqQNB7wiDrmSUIpLTbnMFivytHT7DK1LGgYkRLSGNTeAt8n96_iRtioKdOGgQU2FlMJKZmPECDk3DEWhpCffR9rnOJk1LsbnWSxiobEQmsvI5LnSmMnYwUlxBL1VubLHQFAaa0a6UIIVMotZ7qyMMuKjpLAOxuEJ9L2x5p9No4x5a6fTvx-fwa73RsO7Oodevd7YC9jRX_WiWl8G734DDO2j4w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED2VggRTgYL4xgMjpvVH4pgNVZRWlKhCBXVAqhLbkTq0QU3K78d2osLAwhI58RLdxb4X37t7ADeBkZqknGFOk8hetMIyDSimPCXCulkR41VLRiKOo-lUjhtwu6mFMcZ48pm5c0Ofy9e5Wrujsk4UCJf124LtgHNKqmqtzYkKDSMW1Tkyd8_sv00oo7qfD-nKTu99_OrYXI4-KZ3C-S9BFR9P-q3_vck-HP0U5qHxJuQcQMMsD6FVI0lUr9OiDR8WQ66eHuJ7ZDFl5uaq9tJub0Neg7lI3JeH4ooFXiCLXZEvxsU6XyTzJRou7E6Dyxz7AfIxreLNHcFb_3HSG-BaRwHPLTgoMeOcGU5MKEQgKNVEsExyR78PlMtyEqNtlE-TkIVMiYwpygOdplKJhIcWULJjaC7zpTkBJLg2uqsyyUjGk5Ck1sqCB7QbZcYCOXEKbWes2WfVKmNW2-ns78fXsDuYvIxmo2H8fA57zjMVC-sCmuVqbS5hR32V82J15T39DcMzpyo
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%3Abook&rft.genre=proceeding&rft.title=2018+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=StarGAN%3A+Unified+Generative+Adversarial+Networks+for+Multi-domain+Image-to-Image+Translation&rft.au=Choi%2C+Yunjey&rft.au=Choi%2C+Minje&rft.au=Kim%2C+Munyoung&rft.au=Ha%2C+Jung-Woo&rft.date=2018-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=8789&rft.epage=8797&rft_id=info:doi/10.1109%2FCVPR.2018.00916&rft.externalDocID=8579014