Multi‐Modal Face Stylization with a Generative Prior

In this work, we introduce a new approach for face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generating high‐quality artistic faces with diverse styles and accurate facial reconstruction. Our proposed framework, MMFS, supp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer graphics forum Jg. 42; H. 7
Hauptverfasser: Li, Mengtian, Dong, Yi, Lin, Minxuan, Huang, Haibin, Wan, Pengfei, Ma, Chongyang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Oxford Blackwell Publishing Ltd 01.10.2023
Schlagworte:
ISSN:0167-7055, 1467-8659
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In this work, we introduce a new approach for face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generating high‐quality artistic faces with diverse styles and accurate facial reconstruction. Our proposed framework, MMFS, supports multi‐modal face stylization by leveraging the strengths of StyleGAN and integrates it into an encoder‐decoder architecture. Specifically, we use the mid‐resolution and high‐resolution layers of StyleGAN as the decoder to generate high‐quality faces, while aligning its low‐resolution layer with the encoder to extract and preserve input facial details. We also introduce a two‐stage training strategy, where we train the encoder in the first stage to align the feature maps with StyleGAN and enable a faithful reconstruction of input faces. In the second stage, the entire network is fine‐tuned with artistic data for stylized face generation. To enable the fine‐tuned model to be applied in zero‐shot and one‐shot stylization tasks, we train an additional mapping network from the large‐scale Contrastive‐Language‐Image‐Pre‐training (CLIP) space to a latent w+ space of fine‐tuned StyleGAN. Qualitative and quantitative experiments show that our framework achieves superior performance in both one‐shot and zero‐shot face stylization tasks, outperforming state‐of‐the‐art methods by a large margin.
AbstractList In this work, we introduce a new approach for face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generating high‐quality artistic faces with diverse styles and accurate facial reconstruction. Our proposed framework, MMFS, supports multi‐modal face stylization by leveraging the strengths of StyleGAN and integrates it into an encoder‐decoder architecture. Specifically, we use the mid‐resolution and high‐resolution layers of StyleGAN as the decoder to generate high‐quality faces, while aligning its low‐resolution layer with the encoder to extract and preserve input facial details. We also introduce a two‐stage training strategy, where we train the encoder in the first stage to align the feature maps with StyleGAN and enable a faithful reconstruction of input faces. In the second stage, the entire network is fine‐tuned with artistic data for stylized face generation. To enable the fine‐tuned model to be applied in zero‐shot and one‐shot stylization tasks, we train an additional mapping network from the large‐scale Contrastive‐Language‐Image‐Pre‐training (CLIP) space to a latent w+ space of fine‐tuned StyleGAN. Qualitative and quantitative experiments show that our framework achieves superior performance in both one‐shot and zero‐shot face stylization tasks, outperforming state‐of‐the‐art methods by a large margin.
Author Dong, Yi
Huang, Haibin
Ma, Chongyang
Li, Mengtian
Lin, Minxuan
Wan, Pengfei
Author_xml – sequence: 1
  givenname: Mengtian
  orcidid: 0000-0001-6724-6177
  surname: Li
  fullname: Li, Mengtian
  organization: Kuaishou Technology
– sequence: 2
  givenname: Yi
  orcidid: 0009-0008-8880-0606
  surname: Dong
  fullname: Dong, Yi
  organization: Tsinghua University
– sequence: 3
  givenname: Minxuan
  orcidid: 0009-0006-5130-5754
  surname: Lin
  fullname: Lin, Minxuan
  organization: Kuaishou Technology
– sequence: 4
  givenname: Haibin
  orcidid: 0000-0002-7787-6428
  surname: Huang
  fullname: Huang, Haibin
  email: jackiehuanghaibin@gmail.com
  organization: Kuaishou Technology
– sequence: 5
  givenname: Pengfei
  orcidid: 0000-0001-7225-565X
  surname: Wan
  fullname: Wan, Pengfei
  organization: Kuaishou Technology
– sequence: 6
  givenname: Chongyang
  orcidid: 0000-0002-8243-9513
  surname: Ma
  fullname: Ma, Chongyang
  organization: Kuaishou Technology
BookMark eNp1kM9KAzEQh4NUsK0efIMFTx62TbL5e5RiV6FFQT2HNJtoyrqp2a2lnvoIPqNPYnS9OpcZfnwzA98IDJrQWADOEZygVFPz7CaISIqPwBARxnPBqByAIURp5pDSEzBq2zWEkHBGh4Att3Xnvw6fy1DpOptrY7OHbl_7D9350GQ7371kOittY2NK3m12H32Ip-DY6bq1Z399DJ7m14-zm3xxV97Orha5wZTjXGhkCINGS7IqmBXI8BVDlGDjJHSEYF7YCkFLtZOVpswl0qyIc6LQVVGRYgwu-rubGN62tu3UOmxjk14qLKTAHGEpEnXZUyaGto3WqU30rzruFYLqR4tKWtSvlsROe3bna7v_H1Szct5vfAMdzWWW
Cites_doi 10.1109/TVCG.2021.3114308
10.1109/CVPR52688.2022.01042
10.1145/3450626.3459771
10.1145/3550454.3555437
10.1109/CVPR.2018.00068
10.1109/CVPR.2019.00482
10.1109/CVPR42600.2020.00832
10.1109/CVPR52688.2022.01753
10.1007/978-3-031-19778-9_40
10.1109/CVPR46437.2021.01060
10.1109/ICCV.2017.167
10.1109/ICCV48922.2021.00209
10.1109/CVPR52688.2022.01048
10.1007/s11263-019-01284-z
10.1109/ICCV.2019.00453
10.1109/CVPR52729.2023.00442
10.1109/CVPR.2019.01100
10.1007/978-3-031-25056-9_14
10.1109/ICCV48922.2021.00664
10.1145/3450626.3459860
10.1109/TMM.2021.3113786
10.1145/3306346.3322984
10.1109/CVPR46437.2021.00232
10.1109/CVPR42600.2020.00935
10.1109/ICCV48922.2021.00951
10.1145/3528223.3530164
10.1007/978-3-031-19787-1_8
10.1109/CVPR42600.2020.00821
10.1109/ICCV48922.2021.01368
10.1109/TPAMI.2023.3283551
10.1109/CVPR42600.2020.00813
10.1145/3450626.3459838
10.1109/CVPR52688.2022.00754
10.1109/CVPR.2019.00453
ContentType Journal Article
Copyright 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
2023 The Eurographics Association and John Wiley & Sons Ltd.
Copyright_xml – notice: 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
– notice: 2023 The Eurographics Association and John Wiley & Sons Ltd.
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1111/cgf.14952
DatabaseName CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts

CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1467-8659
EndPage n/a
ExternalDocumentID 10_1111_cgf_14952
CGF14952
Genre article
GroupedDBID .3N
.4S
.DC
.GA
.Y3
05W
0R~
10A
15B
1OB
1OC
29F
31~
33P
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5HH
5LA
5VS
66C
6J9
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
8VB
930
A03
AAESR
AAEVG
AAHQN
AAMMB
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABDPE
ABEML
ABPVW
ACAHQ
ACBWZ
ACCZN
ACFBH
ACGFS
ACPOU
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMLS
ADNMO
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AEIMD
AEMOZ
AENEX
AEUYR
AEYWJ
AFBPY
AFEBI
AFFNX
AFFPM
AFGKR
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGXDD
AGYGG
AHBTC
AHEFC
AHQJS
AIDQK
AIDYY
AIQQE
AITYG
AIURR
AJXKR
AKVCP
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CAG
COF
CS3
CWDTD
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EAD
EAP
EBA
EBO
EBR
EBS
EBU
EDO
EJD
EMK
EST
ESX
F00
F01
F04
F5P
FEDTE
FZ0
G-S
G.N
GODZA
H.T
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
I-F
IHE
IX1
J0M
K1G
K48
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
P2W
P2X
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QWB
R.K
RDJ
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
TH9
TN5
TUS
UB1
V8K
W8V
W99
WBKPD
WIH
WIK
WOHZO
WQJ
WXSBR
WYISQ
WZISG
XG1
ZL0
ZZTAW
~IA
~IF
~WT
AAYXX
CITATION
O8X
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c2572-8a1c460ca94b36e81c7b61542cf90f44273ed10e5af9da56fca9cb4ff83ad3d43
IEDL.DBID DRFUL
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001122395500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-7055
IngestDate Fri Sep 12 11:51:15 EDT 2025
Sat Nov 29 03:41:23 EST 2025
Thu Sep 25 07:34:25 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2572-8a1c460ca94b36e81c7b61542cf90f44273ed10e5af9da56fca9cb4ff83ad3d43
Notes Joint first authors.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-8243-9513
0009-0008-8880-0606
0009-0006-5130-5754
0000-0001-7225-565X
0000-0002-7787-6428
0000-0001-6724-6177
PQID 2898271298
PQPubID 30877
PageCount 10
ParticipantIDs proquest_journals_2898271298
crossref_primary_10_1111_cgf_14952
wiley_primary_10_1111_cgf_14952_CGF14952
PublicationCentury 2000
PublicationDate October 2023
2023-10-00
20231001
PublicationDateYYYYMMDD 2023-10-01
PublicationDate_xml – month: 10
  year: 2023
  text: October 2023
PublicationDecade 2020
PublicationPlace Oxford
PublicationPlace_xml – name: Oxford
PublicationTitle Computer graphics forum
PublicationYear 2023
Publisher Blackwell Publishing Ltd
Publisher_xml – name: Blackwell Publishing Ltd
References 2021; 24
2023
2022
2021
2020
2021; 29
2019
2019; 38
2018
2020; 128
2017
2022; 41
2021; 40
e_1_2_7_5_2
e_1_2_7_3_2
e_1_2_7_9_2
e_1_2_7_7_2
e_1_2_7_19_2
e_1_2_7_17_2
e_1_2_7_15_2
e_1_2_7_13_2
e_1_2_7_41_2
e_1_2_7_11_2
e_1_2_7_43_2
e_1_2_7_45_2
e_1_2_7_47_2
e_1_2_7_26_2
e_1_2_7_49_2
e_1_2_7_28_2
e_1_2_7_50_2
e_1_2_7_25_2
e_1_2_7_52_2
e_1_2_7_23_2
e_1_2_7_31_2
e_1_2_7_54_2
e_1_2_7_21_2
e_1_2_7_33_2
e_1_2_7_35_2
e_1_2_7_37_2
e_1_2_7_39_2
e_1_2_7_4_2
e_1_2_7_2_2
e_1_2_7_8_2
e_1_2_7_6_2
e_1_2_7_18_2
e_1_2_7_16_2
e_1_2_7_14_2
e_1_2_7_40_2
e_1_2_7_12_2
e_1_2_7_42_2
e_1_2_7_10_2
e_1_2_7_44_2
e_1_2_7_46_2
e_1_2_7_48_2
e_1_2_7_27_2
e_1_2_7_29_2
e_1_2_7_24_2
e_1_2_7_30_2
e_1_2_7_51_2
e_1_2_7_22_2
e_1_2_7_32_2
e_1_2_7_53_2
e_1_2_7_20_2
e_1_2_7_34_2
e_1_2_7_55_2
e_1_2_7_36_2
Radford A. (e_1_2_7_38_2) 2021
References_xml – start-page: 8296
  year: 2020
  end-page: 8305
– start-page: 4690
  year: 2019
  end-page: 4699
– start-page: 201
  year: 2023
  end-page: 217
– start-page: 8748
  year: 2021
  end-page: 8763
  article-title: Learning transferable visual models from natural language supervision
– start-page: 10684
  year: 2022
  end-page: 10695
– volume: 40
  start-page: 1
  issue: 4
  year: 2021
  end-page: 13
  article-title: Agilegan: stylizing portraits by inversion-consistent transfer learning
  publication-title: ACM Transactions on Graphics (TOG)
– start-page: 6711
  year: 2021
  end-page: 6720
– start-page: 8780
  year: 2021
  end-page: 8794
– start-page: 10743
  year: 2021
  end-page: 10752
– start-page: 18062
  year: 2022
  end-page: 18071
– volume: 40
  start-page: 1
  issue: 4
  year: 2021
  end-page: 16
  article-title: Stylecarigan: caricature generation via stylegan feature map modulation
  publication-title: ACM Transactions on Graphics (TOG)
– year: 2021
– volume: 41
  start-page: 1
  issue: 6
  year: 2022
  end-page: 15
  article-title: Vtoonify: Controllable high-resolution portrait video style transfer
  publication-title: ACM Transactions on Graphics (TOG)
– start-page: 1501
  year: 2017
  end-page: 1510
– start-page: 29710
  year: 2021
  end-page: 29722
– start-page: 10743
  year: 2019
  end-page: 10752
– volume: 40
  start-page: 1
  issue: 4
  year: 2021
  end-page: 14
  article-title: Designing an encoder for stylegan image manipulation
  publication-title: ACM Transactions on Graphics (TOG)
– start-page: 10748
  year: 2022
  end-page: 10757
– start-page: 4432
  year: 2019
  end-page: 4441
– start-page: 13718
  year: 2022
  end-page: 13730
– start-page: 37297
  year: 2022
  end-page: 37308
– start-page: 7693
  year: 2022
  end-page: 7702
– year: 2018
– start-page: 218
  year: 2018
  end-page: 234
– start-page: 172
  year: 2018
  end-page: 189
– volume: 29
  start-page: 1371
  issue: 2
  year: 2021
  end-page: 1383
  article-title: Exemplar-based 3d portrait stylization
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– start-page: 13921
  year: 2021
  end-page: 13929
– start-page: 4401
  year: 2019
  end-page: 4410
– volume: 38
  start-page: 1
  issue: 4
  year: 2019
  end-page: 15
  article-title: The face of art: landmark detection and geometric style in portraits
  publication-title: ACM Transactions on Graphics (TOG)
– start-page: 8162
  year: 2021
  end-page: 8171
– start-page: 2085
  year: 2021
  end-page: 2094
– start-page: 4552
  year: 2023
  end-page: 4562
– start-page: 2287
  year: 2021
  end-page: 2296
– start-page: 128
  year: 2022
  end-page: 152
– volume: 128
  start-page: 2402
  issue: 10
  year: 2020
  end-page: 2417
  article-title: Drit++: Diverse image-to-image translation via disentangled representations
  publication-title: International Journal of Computer Vision
– start-page: 695
  year: 2022
  end-page: 711
– volume: 24
  start-page: 4077
  year: 2021
  end-page: 4091
  article-title: Anigan: Style-guided generative adversarial networks for unsupervised anime face generation
  publication-title: IEEE Transactions on Multimedia
– year: 2022
– year: 2020
– start-page: 8110
  year: 2020
  end-page: 8119
– year: 2023
– start-page: 9332
  year: 2020
  end-page: 9341
– start-page: 8188
  year: 2020
  end-page: 8197
– year: 2017
– volume: 41
  issue: 4
  year: 2022
  article-title: Stylegan-nada: Clip-guided domain adaptation of image generators
  publication-title: ACM Transactions on Graphics (TOG)
– start-page: 9650
  year: 2021
  end-page: 9660
– ident: e_1_2_7_16_2
  doi: 10.1109/TVCG.2021.3114308
– ident: e_1_2_7_35_2
  doi: 10.1109/CVPR52688.2022.01042
– ident: e_1_2_7_55_2
– start-page: 8748
  volume-title: International Conference on Machine Learning (ICML)
  year: 2021
  ident: e_1_2_7_38_2
– ident: e_1_2_7_39_2
  doi: 10.1145/3450626.3459771
– ident: e_1_2_7_46_2
  doi: 10.1145/3550454.3555437
– ident: e_1_2_7_52_2
  doi: 10.1109/CVPR.2018.00068
– ident: e_1_2_7_24_2
– ident: e_1_2_7_32_2
– ident: e_1_2_7_10_2
  doi: 10.1109/CVPR.2019.00482
– ident: e_1_2_7_50_2
– ident: e_1_2_7_54_2
– ident: e_1_2_7_15_2
– ident: e_1_2_7_5_2
  doi: 10.1109/CVPR42600.2020.00832
– ident: e_1_2_7_22_2
  doi: 10.1109/CVPR52688.2022.01753
– ident: e_1_2_7_6_2
  doi: 10.1007/978-3-031-19778-9_40
– ident: e_1_2_7_31_2
  doi: 10.1109/CVPR46437.2021.01060
– ident: e_1_2_7_29_2
– ident: e_1_2_7_51_2
– ident: e_1_2_7_53_2
– ident: e_1_2_7_13_2
  doi: 10.1109/ICCV.2017.167
– ident: e_1_2_7_33_2
  doi: 10.1109/ICCV48922.2021.00209
– ident: e_1_2_7_41_2
  doi: 10.1109/CVPR52688.2022.01048
– ident: e_1_2_7_26_2
  doi: 10.1007/s11263-019-01284-z
– ident: e_1_2_7_4_2
  doi: 10.1109/ICCV.2019.00453
– ident: e_1_2_7_2_2
  doi: 10.1109/CVPR52729.2023.00442
– ident: e_1_2_7_47_2
  doi: 10.1109/CVPR.2019.01100
– ident: e_1_2_7_30_2
– ident: e_1_2_7_37_2
  doi: 10.1007/978-3-031-25056-9_14
– ident: e_1_2_7_27_2
– ident: e_1_2_7_3_2
  doi: 10.1109/ICCV48922.2021.00664
– ident: e_1_2_7_43_2
– ident: e_1_2_7_18_2
  doi: 10.1145/3450626.3459860
– ident: e_1_2_7_49_2
– ident: e_1_2_7_28_2
  doi: 10.1109/TMM.2021.3113786
– ident: e_1_2_7_48_2
  doi: 10.1145/3306346.3322984
– ident: e_1_2_7_34_2
  doi: 10.1109/CVPR46437.2021.00232
– ident: e_1_2_7_42_2
  doi: 10.1109/CVPR42600.2020.00935
– ident: e_1_2_7_8_2
  doi: 10.1109/ICCV48922.2021.00951
– ident: e_1_2_7_12_2
  doi: 10.1145/3528223.3530164
– ident: e_1_2_7_14_2
– ident: e_1_2_7_11_2
– ident: e_1_2_7_7_2
  doi: 10.1007/978-3-031-19787-1_8
– ident: e_1_2_7_25_2
– ident: e_1_2_7_9_2
  doi: 10.1109/CVPR42600.2020.00821
– ident: e_1_2_7_19_2
  doi: 10.1109/ICCV48922.2021.01368
– ident: e_1_2_7_23_2
  doi: 10.1109/TPAMI.2023.3283551
– ident: e_1_2_7_17_2
– ident: e_1_2_7_21_2
  doi: 10.1109/CVPR42600.2020.00813
– ident: e_1_2_7_36_2
– ident: e_1_2_7_40_2
  doi: 10.1145/3450626.3459838
– ident: e_1_2_7_44_2
– ident: e_1_2_7_45_2
  doi: 10.1109/CVPR52688.2022.00754
– ident: e_1_2_7_20_2
  doi: 10.1109/CVPR.2019.00453
SSID ssj0004765
Score 2.3979654
Snippet In this work, we introduce a new approach for face stylization. Despite existing methods achieving impressive results in this task, there is still room for...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Index Database
Publisher
SubjectTerms CCS Concepts
Coders
Computing methodologies → Image processing
Feature maps
Image reconstruction
Training
Title Multi‐Modal Face Stylization with a Generative Prior
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.14952
https://www.proquest.com/docview/2898271298
Volume 42
WOSCitedRecordID wos001122395500001&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
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1467-8659
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004765
  issn: 0167-7055
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NSwMxEB1K60EPfovVKkE8eFnJbtJkF09SXT3UUtSKtyXJJlKQVrZV8OZP8Df6S0z2o60HQfC2h9llecxM3gyZNwDHFKtAMKU8oQXzqFttErmVYdRyBaMDbop-x0OX93rh42PUr8FZNQtT6EPMGm4uMvJ87QJcyMlCkKsnc-rovc2_jcD6La1D4-I2HnTnY5GctStpbycaUwoLuYs8s5d_HkdzjrnIVPOjJl7710-uw2rJMNF54RIbUNOjTVhZ0B3cApaP3X59fN6MU2saC6XR3fT9uZzJRK45iwQqJKldPkT9bDjOtmEQX953rr1ygYKnbCTaTCd8RRlWIqKSMB36ikvLYGigTIQNpZa66NTHui1MlIo2M9ZSSWpMSERKUkp2oD4aj_QuoBQT6UtLxQkRFEsmjSHclmuYc8JSyZtwVOGYvBQ6GUlVX1gQkhyEJrQqhJMyVCaJrfjCgFvaETbhJMfy9w8knas4f9j7u-k-LLsV8cUFvBbUp9mrPoAl9TYdTrLD0me-Aexfw1s
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NS8NAEB1KK6gHv8Vq1SAevESS7GY3AS9SjRXTUrSV3sJmsysFaSWtgjd_gr_RX-JuPtp6EARvOUxCGObNvhl23gCcYos7jHBuMsGIifVqE1-vDMOKK0jhUJn3Ox5D2ul4g4HfrcBFOQuT60PMGm4aGVm-1gDXDekFlPMnea75vUrANazCyK1C7eo-6IfzuUhK3FLbW6vGFMpC-ibP7OWf59GcZC5S1eysCdb_95cbsFZwTOMyD4pNqIjRFqwuKA9uA8kGb78-PtvjRJkGjAvjYfr-XExlGro9azAjF6XWGdHopsNxugP94LrXbJnFCgWTKyyqXMdsjonFmY9jRIRncxorDoMdLn1LYqzIi0hsS7hM-glziVSWPMZSeoglKMFoF6qj8UjsgZFYKLZjRcYRYtiKSSwloqpgsyhFJIlpHU5KR0YvuVJGVFYYyglR5oQ6NEoXRwVYJpGq-TyHKuLh1eEsc-bvH4iaN0H2sP9302NYbvXaYRTedu4OYEUvjM-v4zWgOk1fxSEs8bfpcJIeFQH0Da81x0s
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB6KFdGDb7FaNYgHL5Eku9lNwIu0RsVailrpLWz2IQVpS1oFb_4Ef6O_xN082noQBG97mA1h2G_2m2HnG4AT7HCPEc5tJhmxsRltEpqRYVhzBSU9qvJ6x1OLtttBrxd2KnBe9sLk-hDTgptBRhavDcDlSKg5lPNndWb4vQ7AVeyHRMOy2ryPuq1ZXyQlfqntbVRjCmUh85JnuvnnfTQjmfNUNbtrorX__eU6rBYc07rID8UGVORgE1bmlAe3gGSNt18fn3dDoU0jxqX1MHl_KboyLVOetZiVi1KbiGh10v4w3YZudPnYuLaLEQo211jUsY65HBOHsxAniMjA5TTRHAZ7XIWOwliTFylcR_pMhYL5RGlLnmClAsQEEhjtwMJgOJC7YAkHJW6iyThCDDsJSZRCVCdsDqWIiITW4Lh0ZDzKlTLiMsPQTogzJ9SgXro4LsAyjnXOF3hUE4-gBqeZM3__QNy4irLF3t9Nj2Cp04zi1k37dh-Wzbz4_DVeHRYm6as8gEX-NumP08Pi_HwDjUfGxg
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=article&rft.atitle=Multi%E2%80%90Modal+Face+Stylization+with+a+Generative+Prior&rft.jtitle=Computer+graphics+forum&rft.au=Li%2C+Mengtian&rft.au=Dong%2C+Yi&rft.au=Lin%2C+Minxuan&rft.au=Huang%2C+Haibin&rft.date=2023-10-01&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=42&rft.issue=7&rft_id=info:doi/10.1111%2Fcgf.14952&rft.externalDBID=n%2Fa&rft.externalDocID=10_1111_cgf_14952
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-7055&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-7055&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-7055&client=summon