Self‐Supervised Image Harmonization via Region‐Aware Harmony Classification
Image harmonization is a widely used technique in image composition, which aims to adjust the appearance of the composited foreground object according to the style of the background image so that the resulting composited image is visually natural and appears to be photographed. Previous methods are...
Uloženo v:
| Vydáno v: | Computer graphics forum Ročník 44; číslo 6 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Oxford
Blackwell Publishing Ltd
01.09.2025
|
| Témata: | |
| ISSN: | 0167-7055, 1467-8659 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Image harmonization is a widely used technique in image composition, which aims to adjust the appearance of the composited foreground object according to the style of the background image so that the resulting composited image is visually natural and appears to be photographed. Previous methods are mostly trained in a fully supervised manner, while demonstrating promising results, they do not generalize well to complex unseen cases involving significant style and semantic difference between the composited foreground object and the background image. In this paper, we present a self‐supervised image harmonization framework that enables superior performance on complex cases. To do so, we first synthesize a large amount of data with wide diversity for training. We then develop an attentive harmonization module to adaptively adjust the foreground appearance by querying relevant background features. To allow more effective image harmonization, we develop a region‐aware harmony classifier to explicitly judge whether an image is harmonious or not. Experiments on several datasets show that our method performs favourably against previous methods. Our code will be made publicly available.
In this paper, we present a self‐supervised image harmonization framework that enables superior performance on complex cases. To do so, we develop an attentive harmonization module and a region‐aware harmony classifier to explicitly judge whether an image is harmonious or not. |
|---|---|
| AbstractList | Image harmonization is a widely used technique in image composition, which aims to adjust the appearance of the composited foreground object according to the style of the background image so that the resulting composited image is visually natural and appears to be photographed. Previous methods are mostly trained in a fully supervised manner, while demonstrating promising results, they do not generalize well to complex unseen cases involving significant style and semantic difference between the composited foreground object and the background image. In this paper, we present a self‐supervised image harmonization framework that enables superior performance on complex cases. To do so, we first synthesize a large amount of data with wide diversity for training. We then develop an attentive harmonization module to adaptively adjust the foreground appearance by querying relevant background features. To allow more effective image harmonization, we develop a region‐aware harmony classifier to explicitly judge whether an image is harmonious or not. Experiments on several datasets show that our method performs favourably against previous methods. Our code will be made publicly available. Image harmonization is a widely used technique in image composition, which aims to adjust the appearance of the composited foreground object according to the style of the background image so that the resulting composited image is visually natural and appears to be photographed. Previous methods are mostly trained in a fully supervised manner, while demonstrating promising results, they do not generalize well to complex unseen cases involving significant style and semantic difference between the composited foreground object and the background image. In this paper, we present a self‐supervised image harmonization framework that enables superior performance on complex cases. To do so, we first synthesize a large amount of data with wide diversity for training. We then develop an attentive harmonization module to adaptively adjust the foreground appearance by querying relevant background features. To allow more effective image harmonization, we develop a region‐aware harmony classifier to explicitly judge whether an image is harmonious or not. Experiments on several datasets show that our method performs favourably against previous methods. Our code will be made publicly available. In this paper, we present a self‐supervised image harmonization framework that enables superior performance on complex cases. To do so, we develop an attentive harmonization module and a region‐aware harmony classifier to explicitly judge whether an image is harmonious or not. |
| Author | Tian, Chenyang Zhang, Qing Wang, Xinbo |
| Author_xml | – sequence: 1 givenname: Chenyang surname: Tian fullname: Tian, Chenyang email: tianchy6@mail2.sysu.edu.cn organization: Sun Yat‐sen University – sequence: 2 givenname: Xinbo surname: Wang fullname: Wang, Xinbo email: wangxb898492298@gmail.com organization: Sun Yat‐sen University – sequence: 3 givenname: Qing surname: Zhang fullname: Zhang, Qing email: zhangq93@mail.sysu.edu.cn organization: Sun Yat‐sen University |
| BookMark | eNp10EtOwzAQBmALFYm2sOAGkVixSOtHHCfLKqIPqVIlCmtr4tqVqzQpdh8qK47AGTkJpoEls5lZfDMj_T3UqZtaI3RP8ICEGqq1GQhMuLhCXZKkIs5SnndQF5MwC8z5Dep5v8EYJyLlXbRY6sp8fXwuDzvtjtbrVTTbwlpHU3DbprbvsLdNHR0tRM96HcZgRydwf-AcFRV4b41VF3mLrg1UXt_99j56HT-9FNN4vpjMitE8VpTnIqZc5QTYSmluiEkzyDQRjDDIVQmpoTjnmgph1KpMDEkYUJGDUQrzMoMy1ayPHtq7O9e8HbTfy01zcHV4KRnljOM0ozSox1Yp13jvtJE7Z7fgzpJg-ZOXDHnJS17BDlt7spU-_w9lMRm3G987XXCS |
| Cites_doi | 10.1109/CVPR52729.2023.01754 10.1109/TIP.2020.2975979 10.1109/CVPR46437.2021.01610 10.1109/TIP.2003.819861 10.1109/CVPR.2018.00068 10.1109/WACV48630.2021.00166 10.1145/1141911.1141934 10.1109/CVPR52729.2023.01362 10.1109/ICCV.2007.4409107 10.1109/ICCV.2017.167 10.1109/CVPR52688.2022.01909 10.1007/978-3-319-46475-6_43 10.1109/CVPR.2019.00603 10.1007/978-3-030-58520-4_35 10.1109/ICCV.2017.146 10.1109/ICCV48922.2021.00658 10.1109/CVPR.2016.265 10.1109/ICME51207.2021.9428394 10.1109/CVPR46437.2021.00294 10.1145/882262.882269 10.1109/CVPR52688.2022.01792 10.1109/CVPR46437.2021.00924 10.1109/CVPR.2019.01030 10.1109/CVPR52729.2023.00574 10.1145/3581783.3612404 10.1109/CVPR42600.2020.00842 10.1109/38.946629 10.1109/ICCV.2019.00913 10.1007/978-3-030-01219-9_28 10.1109/WACV51458.2022.00303 10.1109/CVPR42600.2020.00975 10.1145/2185520.2185580 10.1145/3581783.3611747 10.1145/3652583.3657616 10.1109/CVPR52688.2022.01104 10.1145/1778765.1778862 10.1007/978-3-030-58601-0_34 10.1109/ICCV51070.2023.00371 10.1016/j.cviu.2006.11.011 10.1109/ICCV48922.2021.00986 10.1109/ICCV51070.2023.00688 10.1109/ICCV.2015.314 10.1109/ICCV.2005.166 10.1609/aaai.v34i07.6614 |
| ContentType | Journal Article |
| Copyright | 2025 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd. |
| Copyright_xml | – notice: 2025 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.70157 |
| 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_70157 CGF70157 |
| Genre | researchArticle |
| GrantInformation_xml | – fundername: Guangdong Basic and Applied Basic Research Foundation funderid: 2023A1515030002 – fundername: National Natural Science Foundation of China funderid: 62471499 |
| 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-c2597-25c91a3dce5f1f68a8e17313a9cba6f2095e277fcdb4f143a279afcc05b8ab6e3 |
| IEDL.DBID | DRFUL |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001499813100001&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 | Wed Sep 24 06:01:20 EDT 2025 Sat Nov 29 07:24:12 EST 2025 Wed Sep 24 09:20:27 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c2597-25c91a3dce5f1f68a8e17313a9cba6f2095e277fcdb4f143a279afcc05b8ab6e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| PQID | 3253506822 |
| PQPubID | 30877 |
| PageCount | 13 |
| ParticipantIDs | proquest_journals_3253506822 crossref_primary_10_1111_cgf_70157 wiley_primary_10_1111_cgf_70157_CGF70157 |
| PublicationCentury | 2000 |
| PublicationDate | September 2025 2025-09-00 20250901 |
| PublicationDateYYYYMMDD | 2025-09-01 |
| PublicationDate_xml | – month: 09 year: 2025 text: September 2025 |
| PublicationDecade | 2020 |
| PublicationPlace | Oxford |
| PublicationPlace_xml | – name: Oxford |
| PublicationTitle | Computer graphics forum |
| PublicationYear | 2025 |
| Publisher | Blackwell Publishing Ltd |
| Publisher_xml | – name: Blackwell Publishing Ltd |
| References | 2007; 107 2023 2022 2021 2010; 29 2010 2020 2006; 25 2004; 13 2019 2020; 16 2007 2018 2017 2016 2020; 34 2015 2005; 2 2024 2016; 14 2012; 31 2003; 22 2020; 29 2001; 21 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_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 Vaswani A. (e_1_2_7_45_2) 2017 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_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 Tao M. W. (e_1_2_7_42_2) 2010 e_1_2_7_36_2 e_1_2_7_38_2 |
| References_xml | – volume: 31 issue: 4 year: 2012 article-title: Understanding and improving the realism of image composites publication-title: ACM Transactions on Graphics – volume: 2 start-page: 1434 year: 2005 end-page: 1439 – start-page: 31 year: 2010 end-page: 44 – start-page: 18470 year: 2022 end-page: 18479 article-title: High‐resolution image harmonization via collaborative dual transformations – start-page: 1 year: 2021 end-page: 6 article-title: Bargainnet: Background‐guided domain translation for image harmonization – volume: 29 issue: 4 year: 2010 article-title: Multi‐scale image harmonization publication-title: ACM Transactions on Graphics – start-page: 586 year: 2018 end-page: 595 article-title: The unreasonable effectiveness of deep features as a perceptual metric – start-page: 2159 year: 2023 end-page: 2167 article-title: Deep image harmonization in dual color spaces – start-page: 1422 year: 2023 end-page: 1430 article-title: Hierarchical dynamic image harmonization – start-page: 10012 year: 2021 end-page: 10022 article-title: Swin transformer: Hierarchical vision transformer using shifted windows – start-page: 4015 year: 2023 end-page: 4026 article-title: Segment anything – start-page: 5873 year: 2019 end-page: 5881 article-title: Arbitrary style transfer with style‐attentional networks – year: 2015 article-title: Very deep convolutional networks for large‐scale visual recognition – start-page: 5927 year: 2023 end-page: 5936 article-title: Semi‐supervised parametric real‐world image harmonization – start-page: 3789 year: 2017 end-page: 3797 article-title: Deep image harmonization – start-page: 18290 year: 2023 end-page: 18299 article-title: LEMaRT: Label‐efficient masked region transform for image harmonization – start-page: 7482 year: 2023 end-page: 7491 article-title: Deep image harmonization with learnable augmentation – start-page: 1 year: 2007 end-page: 8 article-title: Using color compatibility for assessing image realism – volume: 13 start-page: 600 issue: 4 year: 2004 end-page: 612 article-title: Image quality assessment: From error visibility to structural similarity publication-title: IEEE Transactions on Image Processing – start-page: 8394 year: 2020 end-page: 8403 article-title: DoveNet: Deep image harmonization via domain verification – start-page: 10061 year: 2019 end-page: 10070 article-title: Inserting videos into videos – start-page: 9036 year: 2019 end-page: 9045 article-title: Photorealistic style transfer via wavelet transforms – start-page: 11326 year: 2022 end-page: 11336 article-title: Stytr2: Image style transfer with transformers – start-page: 9729 year: 2020 end-page: 9738 article-title: Momentum contrast for unsupervised visual representation learning – volume: 34 start-page: 10443 year: 2020 end-page: 10450 article-title: Ultrafast photorealistic style transfer via neural architecture search – start-page: 2414 year: 2016 end-page: 2423 article-title: Image style transfer using convolutional neural networks – start-page: 1301 year: 2017 end-page: 1310 article-title: Cut, paste and learn: Surprisingly easy synthesis for instance detection – start-page: 7535 year: 2023 end-page: 7544 article-title: Learning global‐aware kernel for image harmonization – year: 2017 article-title: A learned representation for artistic style – volume: 107 start-page: 123 issue: 1‐2 year: 2007 end-page: 137 article-title: Automated colour grading using colour distribution transfer publication-title: Computer Vision and Image Understanding – start-page: 1510 year: 2017 end-page: 1519 article-title: Arbitrary style transfer in real‐time with adaptive instance normalization – start-page: 453 year: 2018 end-page: 468 article-title: A closed‐form solution to photorealistic image stylization – start-page: 1130 year: 2024 end-page: 1134 article-title: DiffHarmony: Latent diffusion model meets image harmonization – volume: 16 start-page: 566 year: 2020 end-page: 581 article-title: Learning object placement by inpainting for compositional data augmentation – start-page: 1597 year: 2020 end-page: 1607 article-title: A simple framework for contrastive learning of visual representations – start-page: 9361 year: 2021 end-page: 9370 article-title: Region‐aware adaptive instance normalization for image harmonization – start-page: 19710 year: 2022 end-page: 19719 article-title: SCS‐Co: Self‐consistent style contrastive learning for image harmonization – volume: 25 start-page: 631 issue: 3 year: 2006 end-page: 637 article-title: Drag‐and‐drop pasting publication-title: ACM Transactions on Graphics – volume: 14 start-page: 694 year: 2016 end-page: 711 article-title: Perceptual losses for real‐time style transfer and super‐resolution – start-page: 16362 year: 2021 end-page: 16371 article-title: Intrinsic image harmonization – volume: 29 start-page: 4759 year: 2020 end-page: 4771 article-title: Improving the harmony of the composite image by spatial‐separated attention module publication-title: IEEE Transactions on Image Processing – volume: 22 start-page: 313 issue: 3 year: 2003 end-page: 318 article-title: Poisson image editing publication-title: ACM Transactions on Graphics (TOG) – volume: 21 start-page: 34 issue: 5 year: 2001 end-page: 41 article-title: Color transfer between images publication-title: IEEE Computer Graphics and Applications – start-page: 1619 year: 2021 end-page: 1628 article-title: Foreground‐aware semantic representations for image harmonization – start-page: 14173 year: 2023 end-page: 14182 article-title: Neural preset for color style transfer – start-page: 6649 year: 2021 end-page: 6658 article-title: AdaAttN: Revisit attention mechanism in arbitrary neural style transfer – start-page: 4832 year: 2021 end-page: 4841 article-title: SSH: A self‐supervised framework for image harmonization – year: 2017 – year: 2018 article-title: Video‐to‐video synthesis – start-page: 2918 year: 2021 end-page: 2928 article-title: Simple copy‐paste is a strong data augmentation method for instance segmentation – start-page: 592 year: 2020 end-page: 608 article-title: In‐domain GAN inversion for real image editing – start-page: 2868 year: 2022 end-page: 2877 article-title: PhotoWCT2: Compact autoencoder for photorealistic style transfer resulting from blockwise training and skip connections of high‐frequency residuals – ident: e_1_2_7_26_2 doi: 10.1109/CVPR52729.2023.01754 – start-page: 31 volume-title: ECCV'10: Proceedings of the 11th European Conference on Computer Vision: Part I year: 2010 ident: e_1_2_7_42_2 – ident: e_1_2_7_8_2 doi: 10.1109/TIP.2020.2975979 – ident: e_1_2_7_41_2 – ident: e_1_2_7_16_2 doi: 10.1109/CVPR46437.2021.01610 – ident: e_1_2_7_46_2 doi: 10.1109/TIP.2003.819861 – ident: e_1_2_7_52_2 doi: 10.1109/CVPR.2018.00068 – ident: e_1_2_7_39_2 doi: 10.1109/WACV48630.2021.00166 – ident: e_1_2_7_21_2 doi: 10.1145/1141911.1141934 – ident: e_1_2_7_23_2 doi: 10.1109/CVPR52729.2023.01362 – ident: e_1_2_7_25_2 doi: 10.1109/ICCV.2007.4409107 – ident: e_1_2_7_17_2 doi: 10.1109/ICCV.2017.167 – ident: e_1_2_7_19_2 doi: 10.1109/CVPR52688.2022.01909 – ident: e_1_2_7_20_2 doi: 10.1007/978-3-319-46475-6_43 – ident: e_1_2_7_36_2 doi: 10.1109/CVPR.2019.00603 – ident: e_1_2_7_53_2 doi: 10.1007/978-3-030-58520-4_35 – ident: e_1_2_7_11_2 doi: 10.1109/ICCV.2017.146 – ident: e_1_2_7_28_2 doi: 10.1109/ICCV48922.2021.00658 – ident: e_1_2_7_48_2 – ident: e_1_2_7_15_2 doi: 10.1109/CVPR.2016.265 – ident: e_1_2_7_7_2 doi: 10.1109/ICME51207.2021.9428394 – ident: e_1_2_7_14_2 doi: 10.1109/CVPR46437.2021.00294 – ident: e_1_2_7_33_2 doi: 10.1145/882262.882269 – ident: e_1_2_7_6_2 doi: 10.1109/ICME51207.2021.9428394 – ident: e_1_2_7_9_2 doi: 10.1109/CVPR52688.2022.01792 – ident: e_1_2_7_31_2 doi: 10.1109/CVPR46437.2021.00924 – ident: e_1_2_7_30_2 doi: 10.1109/CVPR.2019.01030 – ident: e_1_2_7_47_2 doi: 10.1109/CVPR52729.2023.00574 – volume-title: Advances in Neural Information Processing Systems year: 2017 ident: e_1_2_7_45_2 – ident: e_1_2_7_5_2 – ident: e_1_2_7_43_2 doi: 10.1145/3581783.3612404 – ident: e_1_2_7_10_2 doi: 10.1109/CVPR42600.2020.00842 – ident: e_1_2_7_37_2 doi: 10.1109/38.946629 – ident: e_1_2_7_50_2 doi: 10.1109/ICCV.2019.00913 – ident: e_1_2_7_29_2 doi: 10.1007/978-3-030-01219-9_28 – ident: e_1_2_7_3_2 doi: 10.1109/WACV51458.2022.00303 – ident: e_1_2_7_18_2 doi: 10.1109/CVPR42600.2020.00975 – ident: e_1_2_7_49_2 doi: 10.1145/2185520.2185580 – ident: e_1_2_7_4_2 doi: 10.1145/3581783.3611747 – ident: e_1_2_7_12_2 – ident: e_1_2_7_51_2 doi: 10.1145/3652583.3657616 – ident: e_1_2_7_13_2 doi: 10.1109/CVPR52688.2022.01104 – ident: e_1_2_7_38_2 doi: 10.1145/1778765.1778862 – ident: e_1_2_7_54_2 doi: 10.1007/978-3-030-58601-0_34 – ident: e_1_2_7_24_2 doi: 10.1109/ICCV51070.2023.00371 – ident: e_1_2_7_22_2 – ident: e_1_2_7_35_2 doi: 10.1016/j.cviu.2006.11.011 – ident: e_1_2_7_27_2 doi: 10.1109/ICCV48922.2021.00986 – ident: e_1_2_7_32_2 doi: 10.1109/ICCV51070.2023.00688 – ident: e_1_2_7_40_2 doi: 10.1109/ICCV.2015.314 – ident: e_1_2_7_34_2 doi: 10.1109/ICCV.2005.166 – ident: e_1_2_7_2_2 doi: 10.1609/aaai.v34i07.6614 – ident: e_1_2_7_44_2 |
| SSID | ssj0004765 |
| Score | 2.4446306 |
| Snippet | Image harmonization is a widely used technique in image composition, which aims to adjust the appearance of the composited foreground object according to the... |
| SourceID | proquest crossref wiley |
| SourceType | Aggregation Database Index Database Publisher |
| SubjectTerms | image and video processing |
| Title | Self‐Supervised Image Harmonization via Region‐Aware Harmony Classification |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.70157 https://www.proquest.com/docview/3253506822 |
| Volume | 44 |
| WOSCitedRecordID | wos001499813100001&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/eLvHCXMwpV1NS8NAEB1q60EPfovVKkE8eIkkmyabxVOpxgpSpbXQW9hsZqWgtSRtxZs_wd_oL3E3Tdp6EARvOUyW8JiPt2HmDcCZr2uSiCyT1QmaquK7JuMYm2gLpHbMLYazZRO03fb7ffZQgstiFmamDzH_4aYjI8vXOsB5lC4FuXiSF1QVM7oCFaL8tl6GylUn6N0txiKp5xbS3lo0JhcW0o0885d_lqMFx1xmqlmpCTb_9ZFbsJEzTKMxc4ltKOFwB9aXdAd34b6Lz_Lr47M7GelUkWJs3L6oxGK0eKLcMh_NNKYDbnRQNywr28YbTwqDdyPbpam7jDLLPegF14_NlplvVjCFuu5oaQbBbO7EAl1pS8_nPtrUsR3ORMQ9SRTvQkKpFHFUl4pRcUIZl0JYbuTzyENnH8rD1yEegOErPiYUzSS2IHW0BHcVpSCSCybR9pmowmkBcDiaCWiExcVDoRNm6FShVkAf5jGUhg5xHdfyFIOpwnkG8u8HhM2bIHs4_LvpEawRvcw3axirQXmcTPAYVsV0PEiTk9yZvgHncs74 |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5qK6gH32K1ahAPXiLJpslmwUup1hZrlT7AW9hsZqWgtfQl3vwJ_kZ_ibtp0taDIHjLYRLCxzy-XWa-ATjzdU0SoWWyIkFTVXzXZBwjE22B1I64xXC6bII2Gv7jI3vIwGU6CzPVh5hduOnIiPO1DnB9Ib0Q5eJJXlBVzegS5IrKjdws5K6alU59PhdJPTfV9taqMYmykO7kmb38sx7NSeYiVY1rTWXjf3-5CesJxzRKU6fYggz2tmFtQXlwB-5b-Cy_Pj5b475OFkOMjNqLSi1GlQ-UYybDmcaky40m6pZlZVt644PU4N2It2nqPqPYchc6let2uWomuxVMoQ48WpxBMJs7kUBX2tLzuY82dWyHMxFyTxLFvJBQKkUUFqXiVJxQxqUQlhv6PPTQ2YNs77WH-2D4ipEJRTSJLUgRLcFdRSqI5IJJtH0m8nCaIhz0pxIaQXr0UOgEMTp5KKTYB0kUDQOHuI5reYrD5OE8Rvn3DwTlm0r8cPB30xNYqbbv6kG91rg9hFWiV_vG7WMFyI4GYzyCZTEZdYeD48SzvgFPo9Lo |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NS8NAEB1qK6IHv8Vq1SAevESSTZPNgpfSGi2WWloFb2GzmZWC1tIv8eZP8Df6S9xNk7YeBMFbDpMlDDPz3oaZNwBnvsYkEVkmKxM0FeK7JuMYm2gLpHbMLYbTZRO02fQfH1krB5fZLMxUH2L2w01nRlKvdYJjP5YLWS6e5AVVaEaXoFB2mafSslBrBw-N-Vwk9dxM21urxqTKQrqTZ_byTzyak8xFqppgTbDxv6_chPWUYxqVaVBsQQ5727C2oDy4A3cdfJZfH5-dcV8XiyHGRv1FlRbjhg9UYKbDmcaky4026pZlZVt544PM4N1ItmnqPqPEchcegqv76o2Z7lYwhbrwaHEGwWzuxAJdaUvP5z7a1LEdzkTEPUkU80JCqRRxVJaKU3FCGZdCWG7k88hDZw_yvdce7oPhK0YmFNEktiBltAR3Fakgkgsm0faZKMJp5uGwP5XQCLOrh_JOmHinCKXM92GaRcPQIa7jWp7iMEU4T7z8-wFh9TpIHg7-bnoCK61aEDbqzdtDWCV6s2_SPVaC_GgwxiNYFpNRdzg4TgPrGx4h0mM |
| 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=Self%E2%80%90Supervised+Image+Harmonization+via+Region%E2%80%90Aware+Harmony+Classification&rft.jtitle=Computer+graphics+forum&rft.au=Tian%2C+Chenyang&rft.au=Wang%2C+Xinbo&rft.au=Zhang%2C+Qing&rft.date=2025-09-01&rft.pub=Blackwell+Publishing+Ltd&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=44&rft.issue=6&rft_id=info:doi/10.1111%2Fcgf.70157&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 |