SMFS‐GAN: Style‐Guided Multi‐class Freehand Sketch‐to‐Image Synthesis

Freehand sketch‐to‐image (S2I) is a challenging task due to the individualized lines and the random shape of freehand sketches. The multi‐class freehand sketch‐to‐image synthesis task, in turn, presents new challenges for this research area. This task requires not only the consideration of the probl...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Computer graphics forum Ročník 43; číslo 6
Hlavní autori:	Cheng, Zhenwei, Wu, Lei, Li, Xiang, Meng, Xiangxu
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Oxford Blackwell Publishing Ltd 01.09.2024
Predmet:	Controllability Datasets image and video processing Image contrast image generation Sketches Synthesis Texture
ISSN:	0167-7055, 1467-8659
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Freehand sketch‐to‐image (S2I) is a challenging task due to the individualized lines and the random shape of freehand sketches. The multi‐class freehand sketch‐to‐image synthesis task, in turn, presents new challenges for this research area. This task requires not only the consideration of the problems posed by freehand sketches but also the analysis of multi‐class domain differences in the conditions of a single model. However, existing methods often have difficulty learning domain differences between multiple classes, and cannot generate controllable and appropriate textures while maintaining shape stability. In this paper, we propose a style‐guided multi‐class freehand sketch‐to‐image synthesis model, SMFS‐GAN, which can be trained using only unpaired data. To this end, we introduce a contrast‐based style encoder that optimizes the network's perception of domain disparities by explicitly modelling the differences between classes and thus extracting style information across domains. Further, to optimize the fine‐grained texture of the generated results and the shape consistency with freehand sketches, we propose a local texture refinement discriminator and a Shape Constraint Module, respectively. In addition, to address the imbalance of data classes in the QMUL‐Sketch dataset, we add 6K images by drawing manually and obtain QMUL‐Sketch+ dataset. Extensive experiments on SketchyCOCO Object dataset, QMUL‐Sketch+ dataset and Pseudosketches dataset demonstrate the effectiveness as well as the superiority of our proposed method. We propose SMFS‐GAN, a style‐guided multiclass freehand sketch‐to‐image synthesis model. We optimize image generation from both style and shape perspectives, enabling the model to generate high‐quality images with controllable style and stable shape from multiclass freehand sketches and style reference images.
AbstractList	Freehand sketch‐to‐image (S2I) is a challenging task due to the individualized lines and the random shape of freehand sketches. The multi‐class freehand sketch‐to‐image synthesis task, in turn, presents new challenges for this research area. This task requires not only the consideration of the problems posed by freehand sketches but also the analysis of multi‐class domain differences in the conditions of a single model. However, existing methods often have difficulty learning domain differences between multiple classes, and cannot generate controllable and appropriate textures while maintaining shape stability. In this paper, we propose a style‐guided multi‐class freehand sketch‐to‐image synthesis model, SMFS‐GAN, which can be trained using only unpaired data. To this end, we introduce a contrast‐based style encoder that optimizes the network's perception of domain disparities by explicitly modelling the differences between classes and thus extracting style information across domains. Further, to optimize the fine‐grained texture of the generated results and the shape consistency with freehand sketches, we propose a local texture refinement discriminator and a Shape Constraint Module, respectively. In addition, to address the imbalance of data classes in the QMUL‐Sketch dataset, we add 6K images by drawing manually and obtain QMUL‐Sketch+ dataset. Extensive experiments on SketchyCOCO Object dataset, QMUL‐Sketch+ dataset and Pseudosketches dataset demonstrate the effectiveness as well as the superiority of our proposed method. Freehand sketch‐to‐image (S2I) is a challenging task due to the individualized lines and the random shape of freehand sketches. The multi‐class freehand sketch‐to‐image synthesis task, in turn, presents new challenges for this research area. This task requires not only the consideration of the problems posed by freehand sketches but also the analysis of multi‐class domain differences in the conditions of a single model. However, existing methods often have difficulty learning domain differences between multiple classes, and cannot generate controllable and appropriate textures while maintaining shape stability. In this paper, we propose a style‐guided multi‐class freehand sketch‐to‐image synthesis model, SMFS‐GAN, which can be trained using only unpaired data. To this end, we introduce a contrast‐based style encoder that optimizes the network's perception of domain disparities by explicitly modelling the differences between classes and thus extracting style information across domains. Further, to optimize the fine‐grained texture of the generated results and the shape consistency with freehand sketches, we propose a local texture refinement discriminator and a Shape Constraint Module, respectively. In addition, to address the imbalance of data classes in the QMUL‐Sketch dataset, we add 6K images by drawing manually and obtain QMUL‐Sketch+ dataset. Extensive experiments on SketchyCOCO Object dataset, QMUL‐Sketch+ dataset and Pseudosketches dataset demonstrate the effectiveness as well as the superiority of our proposed method. We propose SMFS‐GAN, a style‐guided multiclass freehand sketch‐to‐image synthesis model. We optimize image generation from both style and shape perspectives, enabling the model to generate high‐quality images with controllable style and stable shape from multiclass freehand sketches and style reference images. Freehand sketch‐to‐image (S2I) is a challenging task due to the individualized lines and the random shape of freehand sketches. The multi‐class freehand sketch‐to‐image synthesis task, in turn, presents new challenges for this research area. This task requires not only the consideration of the problems posed by freehand sketches but also the analysis of multi‐class domain differences in the conditions of a single model. However, existing methods often have difficulty learning domain differences between multiple classes, and cannot generate controllable and appropriate textures while maintaining shape stability. In this paper, we propose a style‐guided multi‐class freehand sketch‐to‐image synthesis model, SMFS‐GAN, which can be trained using only unpaired data. To this end, we introduce a contrast‐based style encoder that optimizes the network's perception of domain disparities by explicitly modelling the differences between classes and thus extracting style information across domains. Further, to optimize the fine‐grained texture of the generated results and the shape consistency with freehand sketches, we propose a local texture refinement discriminator and a Shape Constraint Module, respectively. In addition, to address the imbalance of data classes in the QMUL‐Sketch dataset, we add 6K images by drawing manually and obtain QMUL‐Sketch+ dataset. Extensive experiments on SketchyCOCO Object dataset, QMUL‐Sketch+ dataset and Pseudosketches dataset demonstrate the effectiveness as well as the superiority of our proposed method.
Author	Li, Xiang Cheng, Zhenwei Meng, Xiangxu Wu, Lei
Author_xml	– sequence: 1 givenname: Zhenwei orcidid: 0009-0008-6838-8634 surname: Cheng fullname: Cheng, Zhenwei email: 202135253@mail.sdu.edu.cn organization: Shandong University – sequence: 2 givenname: Lei orcidid: 0000-0002-3872-9062 surname: Wu fullname: Wu, Lei email: i_lily@sdu.edu.cn organization: Shandong University – sequence: 3 givenname: Xiang surname: Li fullname: Li, Xiang email: xiangli_@mail.sdu.edu.cn organization: Shandong University – sequence: 4 givenname: Xiangxu surname: Meng fullname: Meng, Xiangxu email: mxx@sdu.edu.cn organization: Shandong University
BookMark	eNp1kM9Og0AQxjemJrbVg29A4skD7S7sH_DWNIJNWntAz5uFHVoqhcpCDDcfwWf0SdyKV-cwM9_kNzPJN0Gjqq4AoVuCZ8TGPNvlM8JIiC_QmFAu3ICzcITGmNheYMau0MSYA8aYCs7GaJtsouT78ytePD84SduXcBZdoUE7m65sCyuzUhnjRA3AXlXaSd6gzfZ23tY2rY5qB07SV-0eTGGu0WWuSgM3f3WKXqPHl-WTu97Gq-Vi7WYeE9jlmQhyij0_FTiFjHKf5TnVIfWBelT7oQgFSRULeBrgkAeBJprmHlUpVkR74E_R3XD31NTvHZhWHuquqexL6RMcCEEx9yx1P1BZUxvTQC5PTXFUTS8Jlme_pPVL_vpl2fnAfhQl9P-DchlHw8YP1-NwtA
Cites_doi	10.1145/3394171.3413684 10.1609/aaai.v38i5.28226 10.1609/aaai.v35i3.16368 10.1145/1618452.1618470 10.1109/MCG.2011.67 10.1109/TMM.2020.3015015 10.1109/ICCV51070.2023.00355 10.1145/3343031.3350854 10.1007/978-3-030-01270-0_13 10.1007/978-3-030-58580-8_3 10.1109/ACCESS.2019.2913178 10.1145/3503161.3548415 10.1016/j.neucom.2021.07.029 10.1007/978-3-031-19787-1_36 10.1109/ICASSP43922.2022.9747480 10.1145/3588432.3591560 10.1609/aaai.v35i3.16304
ContentType	Journal Article
Copyright	2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
Copyright_xml	– notice: 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
DBID	AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1111/cgf.15190
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	CrossRef Computer and Information Systems Abstracts
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1467-8659
EndPage	n/a
ExternalDocumentID	10_1111_cgf_15190 CGF15190
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 AAHHS AAHQN AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABDBF ABDPE ABEML ABPVW ACAHQ ACBWZ ACCFJ ACCZN ACFBH ACGFS ACPOU ACRPL ACSCC ACUHS ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN ADZOD AEEZP AEGXH AEIGN AEIMD AEMOZ AENEX AEQDE AEUQT AEUYR AFBPY AFEBI AFFNX AFFPM AFGKR AFPWT AFWVQ AFZJQ AHBTC AHEFC AHQJS AITYG AIURR AIWBW AJBDE 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 WRC WXSBR WYISQ WZISG XG1 ZL0 ZZTAW ~IA ~IF ~WT AAMMB AAYXX ADMLS AEFGJ AEYWJ AGHNM AGQPQ AGXDD AGYGG AIDQK AIDYY AIQQE CITATION O8X 7SC 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c2570-6c78f4023b70bec4635ff4d943e424d397971ba586b809688d1d4f24ab0a1d2e3
IEDL.DBID	DRFUL
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001284990100001&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	Sat Jul 26 01:35:55 EDT 2025 Sat Nov 29 03:41:23 EST 2025 Wed Jan 22 17:14:26 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	6
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c2570-6c78f4023b70bec4635ff4d943e424d397971ba586b809688d1d4f24ab0a1d2e3
Notes	Corresponding author i_lily@sdu.edu.cn ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-3872-9062 0009-0008-6838-8634
PQID	3108774062
PQPubID	30877
PageCount	13
ParticipantIDs	proquest_journals_3108774062 crossref_primary_10_1111_cgf_15190 wiley_primary_10_1111_cgf_15190_CGF15190
PublicationCentury	2000
PublicationDate	September 2024 2024-09-00 20240901
PublicationDateYYYYMMDD	2024-09-01
PublicationDate_xml	– month: 09 year: 2024 text: September 2024
PublicationDecade	2020
PublicationPlace	Oxford
PublicationPlace_xml	– name: Oxford
PublicationTitle	Computer graphics forum
PublicationYear	2024
Publisher	Blackwell Publishing Ltd
Publisher_xml	– name: Blackwell Publishing Ltd
References	2021; 35 2019; 7 2020; 4 2023 2022 2021 2020 2014; 27 2019 2018 2017 2016 2020; 23 2021; 460 2009; 5 2020; 33 2014 2016; 29 2011; 6 2024; 38 Baek K. (e_1_2_7_3_2) 2021 e_1_2_7_9_2 Ghosh A. (e_1_2_7_10_2) 2019 Zhao B. (e_1_2_7_46_2) 2019 e_1_2_7_7_2 e_1_2_7_19_2 e_1_2_7_15_2 Karras T. (e_1_2_7_18_2) 2020 e_1_2_7_14_2 Singh S. (e_1_2_7_33_2) 2020 Wang S.‐Y. (e_1_2_7_39_2) 2021 e_1_2_7_40_2 e_1_2_7_13_2 e_1_2_7_41_2 e_1_2_7_12_2 e_1_2_7_44_2 e_1_2_7_45_2 Zhu J.‐Y. (e_1_2_7_47_2) 2017 Koley S. (e_1_2_7_17_2) 2023 e_1_2_7_27_2 e_1_2_7_28_2 Isola P. (e_1_2_7_16_2) 2017 Chen T. (e_1_2_7_4_2) 2009; 5 Song J. (e_1_2_7_35_2) 2020 Reed S. (e_1_2_7_31_2) 2016 An Z. (e_1_2_7_2_2) 2023 Sun W. (e_1_2_7_36_2) 2019 He K. (e_1_2_7_11_2) 2020 e_1_2_7_25_2 e_1_2_7_24_2 e_1_2_7_30_2 e_1_2_7_23_2 e_1_2_7_22_2 Xian W. (e_1_2_7_43_2) 2018 e_1_2_7_21_2 Sangkloy P. (e_1_2_7_34_2) 2017 e_1_2_7_20_2 e_1_2_7_37_2 Mirza M. (e_1_2_7_26_2) 2014 e_1_2_7_38_2 Gao C. (e_1_2_7_8_2) 2020 Qin C. (e_1_2_7_29_2) 2023 Rombach R. (e_1_2_7_32_2) 2022 Xiang X. (e_1_2_7_42_2) 2022 Chen S.‐Y. (e_1_2_7_6_2) 2020; 4 Chen W. (e_1_2_7_5_2) 2018
References_xml	– start-page: 632 year: 2022 end-page: 650 article-title: CoGS: Controllable generation and search from sketch and style – volume: 33 start-page: 7198 year: 2020 end-page: 7211 article-title: Swapping autoencoder for deep image manipulation – start-page: 205 year: 2018 end-page: 220 article-title: Image generation from sketch constraint using contextual GAN – start-page: 1171 year: 2019 end-page: 1180 article-title: Interactive sketch & fill: Multiclass sketch‐to‐image translation publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – start-page: 5400 year: 2017 end-page: 5409 article-title: Scribbler: Controlling deep image synthesis with sketch and color publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 6 start-page: 56 year: 2011 end-page: 66 article-title: Photosketcher: interactive sketch‐based image synthesis publication-title: IEEE Computer Graphics and Applications – start-page: 42961 year: 2023 end-page: 42992 – volume: 29 start-page: 1 year: 2016 end-page: 9 article-title: Learning what and where to draw – volume: 5 start-page: 1 year: 2009 end-page: 10 article-title: Sketch2Photo: Internet image montage publication-title: ACM Transactions on Graphics (TOG) – start-page: 2223 year: 2017 end-page: 2232 article-title: Unpaired image‐to‐image translation using cycle‐consistent adversarial networks publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 36 year: 2020 end-page: 52 article-title: Unsupervised sketch to photo synthesis – start-page: 4319 year: 2023 end-page: 4329 article-title: SketchInverter: Multi‐class sketch‐based image generation via GAN inversion publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision – start-page: 9416 year: 2018 end-page: 9425 article-title: SketchyGAN: Towards diverse and realistic sketch to image synthesis publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 14154 year: 2021 end-page: 14163 article-title: Rethinking the truly unsupervised image‐to‐image translation publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – start-page: 1125 year: 2017 end-page: 1134 article-title: Image‐to‐image translation with conditional adversarial networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 6850 year: 2023 end-page: 6861 article-title: Picture that sketch: Photorealistic image generation from abstract sketches publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 14050 year: 2021 end-page: 14060 article-title: Sketch your own GAN publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – start-page: 5174 year: 2020 end-page: 5183 article-title: SketchyCOCO: Image generation from freehand scene sketches publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 10684 year: 2022 end-page: 10695 article-title: High‐resolution image synthesis with latent diffusion models publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 1 year: 2022 end-page: 14 article-title: DifFSketching: Sketch control image synthesis with diffusion models – volume: 38 start-page: 4296 issue: 5 year: 2024 end-page: 4304 article-title: T2I‐Adapter: Learning Adapters to Dig Out More Controllable Ability for Text‐to‐Image Diffusion Models – start-page: 10531 year: 2019 end-page: 10540 article-title: Image synthesis from reconfigurable layout and style publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – start-page: 991 year: 2020 end-page: 999 article-title: DeepFacePencil: Creating face images from freehand sketches publication-title: Proceedings of the 28th ACM International Conference on Multimedia – start-page: 8456 year: 2018 end-page: 8465 article-title: TextureGAN: Controlling deep image synthesis with texture patches publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 33 start-page: 6840 year: 2020 end-page: 6851 article-title: Denoising diffusion probabilistic models – volume: 35 start-page: 2647 year: 2021 end-page: 2655 article-title: Object‐centric image generation from layouts – start-page: 1 end-page: 11 article-title: Sketch‐guided text‐to‐image diffusion models – start-page: 1060 year: 2016 end-page: 1069 article-title: Generative adversarial text to image synthesis publication-title: International Conference on Machine Learning – start-page: 8110 year: 2020 end-page: 8119 article-title: Analyzing and improving the image quality of StyleGAN publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 11237 year: 2020 end-page: 11246 article-title: Filter response normalization layer: Eliminating batch dependence in the training of deep neural networks publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 1 end-page: 11 – start-page: 9729 year: 2020 end-page: 9738 article-title: Momentum contrast for unsupervised visual representation learning publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 3836 year: 2023 end-page: 3847 article-title: Adding conditional control to text‐to‐image diffusion models – start-page: 1 year: 2020 end-page: 22 – volume: 4 start-page: 72:1 year: 2020 end-page: 72:16 article-title: DeepFaceDrawing: Deep generation of face images from sketches publication-title: ACM Transactions on Graphics (TOG) – volume: 23 start-page: 2694 year: 2020 end-page: 2705 article-title: Staged sketch‐to‐image synthesis via semi‐supervised generative adversarial networks publication-title: IEEE Transactions on Multimedia – start-page: 2073 year: 2021 end-page: 2081 article-title: Self‐supervised sketch‐to‐image synthesis publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – start-page: 2323 year: 2019 end-page: 2331 article-title: LinesToFacePhoto: Face photo generation from lines with conditional self‐attention generative adversarial networks publication-title: Proceedings of the 27th ACM International Conference on Multimedia – start-page: 8584 year: 2019 end-page: 8593 article-title: Image generation from layout publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 1 year: 2014 end-page: 7 article-title: Conditional generative adversarial nets publication-title: arXiv preprint arXiv:1411.1784 – start-page: 3723 year: 2022 end-page: 3727 article-title: Natural‐looking adversarial examples from freehand sketches – volume: 7 start-page: 56683 year: 2019 end-page: 56693 article-title: Multi‐instance sketch to image synthesis with progressive generative adversarial networks publication-title: IEEE Access – start-page: 1434 year: 2022 end-page: 1444 article-title: Adversarial open domain adaptation for sketch‐to‐photo synthesis publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision – volume: 27 year: 2014 article-title: Generative adversarial nets – start-page: 2229 year: 2022 end-page: 2238 article-title: Customizing GAN using few‐shot sketches publication-title: Proceedings of the 30th ACM International Conference on Multimedia – volume: 460 start-page: 256 year: 2021 end-page: 265 article-title: Cali‐Sketch: Stroke calibration and completion for high‐quality face image generation from human‐like sketches publication-title: Neurocomputing – ident: e_1_2_7_21_2 doi: 10.1145/3394171.3413684 – start-page: 1 year: 2014 ident: e_1_2_7_26_2 article-title: Conditional generative adversarial nets publication-title: arXiv preprint arXiv:1411.1784 – ident: e_1_2_7_13_2 – start-page: 5174 year: 2020 ident: e_1_2_7_8_2 article-title: SketchyCOCO: Image generation from freehand scene sketches publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – ident: e_1_2_7_30_2 – start-page: 9416 year: 2018 ident: e_1_2_7_5_2 article-title: SketchyGAN: Towards diverse and realistic sketch to image synthesis publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – ident: e_1_2_7_27_2 doi: 10.1609/aaai.v38i5.28226 – start-page: 10684 year: 2022 ident: e_1_2_7_32_2 article-title: High‐resolution image synthesis with latent diffusion models publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 4319 year: 2023 ident: e_1_2_7_2_2 article-title: SketchInverter: Multi‐class sketch‐based image generation via GAN inversion publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision – start-page: 8110 year: 2020 ident: e_1_2_7_18_2 article-title: Analyzing and improving the image quality of StyleGAN publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – ident: e_1_2_7_37_2 doi: 10.1609/aaai.v35i3.16368 – start-page: 6850 year: 2023 ident: e_1_2_7_17_2 article-title: Picture that sketch: Photorealistic image generation from abstract sketches publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 5 start-page: 1 year: 2009 ident: e_1_2_7_4_2 article-title: Sketch2Photo: Internet image montage publication-title: ACM Transactions on Graphics (TOG) doi: 10.1145/1618452.1618470 – volume: 4 start-page: 72:1 year: 2020 ident: e_1_2_7_6_2 article-title: DeepFaceDrawing: Deep generation of face images from sketches publication-title: ACM Transactions on Graphics (TOG) – start-page: 14050 year: 2021 ident: e_1_2_7_39_2 article-title: Sketch your own GAN publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – ident: e_1_2_7_7_2 doi: 10.1109/MCG.2011.67 – ident: e_1_2_7_24_2 doi: 10.1109/TMM.2020.3015015 – ident: e_1_2_7_45_2 doi: 10.1109/ICCV51070.2023.00355 – ident: e_1_2_7_20_2 doi: 10.1145/3343031.3350854 – ident: e_1_2_7_9_2 – ident: e_1_2_7_12_2 – start-page: 1171 year: 2019 ident: e_1_2_7_10_2 article-title: Interactive sketch & fill: Multiclass sketch‐to‐image translation publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – ident: e_1_2_7_22_2 doi: 10.1007/978-3-030-01270-0_13 – ident: e_1_2_7_23_2 doi: 10.1007/978-3-030-58580-8_3 – ident: e_1_2_7_41_2 doi: 10.1109/ACCESS.2019.2913178 – start-page: 10531 year: 2019 ident: e_1_2_7_36_2 article-title: Image synthesis from reconfigurable layout and style publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – start-page: 14154 year: 2021 ident: e_1_2_7_3_2 article-title: Rethinking the truly unsupervised image‐to‐image translation publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – start-page: 1060 year: 2016 ident: e_1_2_7_31_2 article-title: Generative adversarial text to image synthesis publication-title: International Conference on Machine Learning – start-page: 1434 year: 2022 ident: e_1_2_7_42_2 article-title: Adversarial open domain adaptation for sketch‐to‐photo synthesis publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision – ident: e_1_2_7_15_2 doi: 10.1145/3503161.3548415 – start-page: 42961 volume-title: Proceedings of the 37th International Conference on Neural Information Processing Systems year: 2023 ident: e_1_2_7_29_2 – start-page: 1 volume-title: International Conference on Learning Representations year: 2020 ident: e_1_2_7_35_2 – start-page: 1125 year: 2017 ident: e_1_2_7_16_2 article-title: Image‐to‐image translation with conditional adversarial networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – ident: e_1_2_7_44_2 doi: 10.1016/j.neucom.2021.07.029 – start-page: 2223 year: 2017 ident: e_1_2_7_47_2 article-title: Unpaired image‐to‐image translation using cycle‐consistent adversarial networks publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 9729 year: 2020 ident: e_1_2_7_11_2 article-title: Momentum contrast for unsupervised visual representation learning publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – ident: e_1_2_7_14_2 doi: 10.1007/978-3-031-19787-1_36 – start-page: 8584 year: 2019 ident: e_1_2_7_46_2 article-title: Image generation from layout publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – ident: e_1_2_7_19_2 doi: 10.1109/ICASSP43922.2022.9747480 – ident: e_1_2_7_40_2 – ident: e_1_2_7_38_2 doi: 10.1145/3588432.3591560 – start-page: 8456 year: 2018 ident: e_1_2_7_43_2 article-title: TextureGAN: Controlling deep image synthesis with texture patches publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 5400 year: 2017 ident: e_1_2_7_34_2 article-title: Scribbler: Controlling deep image synthesis with sketch and color publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – ident: e_1_2_7_25_2 doi: 10.1609/aaai.v35i3.16304 – ident: e_1_2_7_28_2 – start-page: 11237 year: 2020 ident: e_1_2_7_33_2 article-title: Filter response normalization layer: Eliminating batch dependence in the training of deep neural networks publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
SSID	ssj0004765
Score	2.4147308
Snippet	Freehand sketch‐to‐image (S2I) is a challenging task due to the individualized lines and the random shape of freehand sketches. The multi‐class freehand...
SourceID	proquest crossref wiley
SourceType	Aggregation Database Index Database Publisher
SubjectTerms	Controllability Datasets image and video processing Image contrast image generation Sketches Synthesis Texture
Title	SMFS‐GAN: Style‐Guided Multi‐class Freehand Sketch‐to‐Image Synthesis
URI	https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.15190 https://www.proquest.com/docview/3108774062
Volume	43
WOSCitedRecordID	wos001284990100001&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/eLvHCXMwpV1LS8NAEB5K60EPvsVqlSAevESSzTYPPZVqqlCrGCu9hWyyK0VNpUmF3vwJ_kZ_ibN5tPUgCF5CNiRhmZ3HN7s73wIcE6aRSMsNiaqUhJbKzEBg1srQ-QmiGxnZ82PX6vXswcC5q8B5WQuT80PMJtykZWT-Whp4wJIFIw-fxCmGKwfz9RpBvW1WoXZx7_a787JIy2yW1N6SNKYgFpIbeWYf_wxHc4y5iFSzUOOu_auT67BaIEyllavEBlR4vAkrC7yDW3Dr3bje18dnp9U7U7x0-sJlYzKMeKRkFbnYDCWsVtwx53JuXfGe5fji83SEl-tXdEOKN40RPibDZBv67uVD-0otTlZQQ3lqnWqGli0wczSYpeEgUkQdQtDIoQanhEZyrc_SWdC0TWZjjmPbkR5RQWjAtECPCDd2oBqPYr4LisMMHtBQYA8DqlvCCZgIHS4QpjFuEr0OR6WA_becQMMvEw-Ujp9Jpw6NUvR-YUOJj8DTRnCqmaQOJ5mQf_-B3-642c3e31_dh2WCCCXfMNaAajqe8ANYCt_TYTI-LJTpG24sz5o
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5KK6gH32K1ahAPXiLJZpuHeCnV2GJbxbTSW8gmu1LUVvoQevMn-Bv9Jc7m0daDIHgJ2ZCEZXYe38zufgtwSphGIi0xJKpSEloqMwOBWStD5yeIbsRkz48Nq9Wyu13nPgeX2V6YhB9iVnCTlhH7a2ngsiC9YOXhkzjHeOVgwl6gqEao34WrB7fTmO-LtMxyxu0tWWNSZiG5kmf28c94NAeZi1A1jjXu-v96uQFrKcZUKolSbEKO97dgdYF5cBvuvKbrfX183lRaF4o3nr5w2Zj0Ih4p8Z5cbIYSWCvukHNZXVe8ZznC-Hw8wEv9FR2R4k37CCBHvdEOdNzrdrWmpmcrqKE8t041Q8sWmDsazNJwGFF-ZSFo5FCDU0IjOdtn6Swo2yazMcux7UiPqCA0YFqgR4Qbu5DvD_p8DxSHGTygocAeBlS3hBMwETpcIFBj3CR6EU4yCftvCYWGn6UeKB0_lk4RSpns_dSKRj5CTxvhqWaSIpzFUv79B371xo1v9v_-6jEs19rNht-ot24PYIUgXkmWj5UgPx5O-CEshe_j3mh4lGrWN9xV04o
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5KK6IH32K1ahAPXiLJZpuHeCmtqWKtxVjpLWSzu1LUKn0IvfkT_I3-Emfz0HoQBC8hG5KwzO7MfLO78w3AIWEG4UaqSFSnJHZ0ZkcSo1aGxk8S00rInu9aTrvt9npepwCneS5Myg_xteCmNCOx10rBxQuXM1oe38tj9FceBuwlqorIFKHUuPG7re-8SMeu5tzeijUmYxZSJ3m-Pv7pj75B5ixUTXyNv_y_Xq7AUoYxtVo6KVahIAZrsDjDPLgO18GVH3y8vTdr7RMtGE8fhWpM-lxwLcnJxWasgLXmD4VQq-ta8KBGGJ-Pn_Fy8YSGSAumAwSQo_5oA7r-2W39XM9qK-ixqlun27HjSowdLeYYOIwUcYeUlHvUEpRQrnb7HJNFVddmLkY5rstNTiWhETMikxNhbUJx8DwQW6B5zBIRjSX2MKKmI72IydgTEoEaEzYxy3CQSzh8SSk0wjz0QOmEiXTKUMllH2ZaNAoReroITw2blOEokfLvPwjrTT-52f77q_sw32n4YeuifbkDCwThSnp6rALF8XAidmEufh33R8O9bGJ9Aqow0wU
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=SMFS%E2%80%90GAN%3A+Style%E2%80%90Guided+Multi%E2%80%90class+Freehand+Sketch%E2%80%90to%E2%80%90Image+Synthesis&rft.jtitle=Computer+graphics+forum&rft.au=Cheng%2C+Zhenwei&rft.au=Wu%2C+Lei&rft.au=Li%2C+Xiang&rft.au=Meng%2C+Xiangxu&rft.date=2024-09-01&rft.pub=Blackwell+Publishing+Ltd&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=43&rft.issue=6&rft_id=info:doi/10.1111%2Fcgf.15190&rft.externalDBID=NO_FULL_TEXT
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