{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:18:39Z","timestamp":1756991919901,"version":"3.41.2"},"reference-count":55,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2024,5]]},"abstract":"<jats:title>Summary<\/jats:title><jats:p>Prior knowledge plays a crucial role in image completion. Although almost all of the existing image completion methods use prior knowledge to complete the image to be repaired from different perspectives, the learning and modeling of the prior knowledge is still a challenging problem. In order to address this issue, we propose a novel prior knowledge distillation framework (PKD\u2010Net) which could distill prior knowledge of structure and style from multiple semantic space and generates not only plausible content but also consistent style with surrounding image area. Our PKD\u2010Net replaces the skip connection in the vanilla U\u2010Net with a semantic shift attention module. The semantic shift attention module takes features from encoder layer and those from decoder layer as input pairs to output shifted features which take into account the long\u2010range dependency of encoder layer features and corresponding decoder layer features from the perspective of local structure and style. Semantic shift attention module models the global interdependencies in local spatial structures (patches centered at each position) and style (appearance texture) dimensions respectively, which could implement distillation of prior knowledge from two aspects: structure and style. Experiments on multiple datasets including faces (CelebA, CelebA\u2010HQ) and natural images (ImageNet, Places2, Paris Street View) demonstrate that our proposed approach generates higher quality completion results than existing ones.<\/jats:p>","DOI":"10.1002\/cpe.7960","type":"journal-article","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T10:11:47Z","timestamp":1702548707000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["<scp>PKD\u2010Net<\/scp>: Distillation of prior knowledge for image completion by multi\u2010level semantic attention"],"prefix":"10.1002","volume":"36","author":[{"given":"Qiong","family":"Lu","sequence":"first","affiliation":[{"name":"School of Media Engineering Communication University of Zhejiang  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaizhong","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Zhejiang University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Xing","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Zhejiang University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Zhejiang University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1737-3420","authenticated-orcid":false,"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Digital Urban Governance Zhejiang University City College  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,12,13]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"e_1_2_8_3_1","doi-asserted-by":"crossref","unstructured":"LiuH JiangB XiaoY YangC.Coherent semantic attention for image inpainting. Paper presented at: International Conference on Computer Vision.2019.","DOI":"10.1109\/ICCV.2019.00427"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"e_1_2_8_5_1","doi-asserted-by":"crossref","unstructured":"LevinA ZometA PelegS WeissY.Seamless image stitching in the gradient domain. Paper presented at: European Conference on Computer Vision 377\u2013389. Springer.2004.","DOI":"10.1007\/978-3-540-24673-2_31"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/83.935036"},{"key":"e_1_2_8_7_1","first-page":"346","article-title":"Image quilting for texture synthesis","volume":"341","author":"Efros A","year":"2001","journal-title":"Proceed SIGGRAPH"},{"key":"e_1_2_8_8_1","first-page":"2672","article-title":"Generative adversarial nets","author":"Goodfellow I","year":"2014","journal-title":"Adv Neur Inform Process Syst"},{"key":"e_1_2_8_9_1","doi-asserted-by":"crossref","unstructured":"PathakD KrahenbuhlP DonahueJ DarrellT EfrosAA.Context encoders: feature learning by inpainting. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2536\u20132544.2016.","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_2_8_10_1","unstructured":"ZhangH GoodfellowI MetaxasD OdenaA.Self\u2010attention generative adversarial networks. arXiv preprint arXiv:1805.08318.2018."},{"key":"e_1_2_8_11_1","unstructured":"GatysLA EckerAS BethgeM.A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576.2015."},{"key":"e_1_2_8_12_1","doi-asserted-by":"crossref","unstructured":"WangH LiY WangY HuH YangM\u2010H.Collaborative distillation for ultra\u2010resolution universal style transfer. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2020.","DOI":"10.1109\/CVPR42600.2020.00193"},{"key":"e_1_2_8_13_1","doi-asserted-by":"crossref","unstructured":"LiuZ LuoP WangX TangX.Deep learning face attributes in the wild. Paper presented at: Proceedings of the IEEE International Conference on Computer Vision 3730\u20133738.2015.","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_2_8_14_1","unstructured":"KarrasT AilaT LaineS LehtinenJ.Progressive Growing of GANs for Improved Quality Stability and Variation.2017."},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185597"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","unstructured":"ZhouB LapedrizaA KhoslaA OlivaA TorralbaA.Places: a 10 million image database for scene recognition. Paper presented at: IEEE Transactions on Pattern Analysis and Ma\u2010 Chine Intelligence.2017;40(6):1452\u20101464.","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"e_1_2_8_18_1","doi-asserted-by":"crossref","unstructured":"SimakovD CaspiY ShechtmanE IraniM.Summarizing visual data using bidirectional similarity. Paper presented at: 2008 IEEE Conference on Computer Vision and Pattern Recognition 1\u20138. IEEE.2008.","DOI":"10.1109\/CVPR.2008.4587842"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"GuoZ ChenZ YuT ChenJ LiuS.Progressive image inpainting with full\u2010resolution residual network. Paper presented at: Proceedings of the 27th ACM International Conference on Multimedia 2496\u20132504. ACM.2019.","DOI":"10.1145\/3343031.3351022"},{"key":"e_1_2_8_20_1","unstructured":"NazeriK NgE JosephT QureshiF EbrahimiM.Edgeconnect: Generative image inpainting with adversarial edge learning. arXiv preprint arXiv:1901.00212.2019."},{"key":"e_1_2_8_21_1","unstructured":"ParkDY LeeKH.Arbitrary Style Transfer with Style\u2010Attentional Networks. arXiv preprint arXiv:1812.02342.2018."},{"key":"e_1_2_8_22_1","unstructured":"WangY TaoX QiX ShenX JiaJ.Image inpainting via generative multi\u2010column convolutional neural networks. Paper presented at: Advances in Neural Information Processing Systems 331\u2013340.2018."},{"key":"e_1_2_8_23_1","doi-asserted-by":"crossref","unstructured":"XieC LiuS LiC et al.Image inpainting with learnable bidirectional attention maps. Paper presented at: Proceedings of the IEEE International Conference on Computer Vision 8858\u20138867.2019.","DOI":"10.1109\/ICCV.2019.00895"},{"key":"e_1_2_8_24_1","doi-asserted-by":"crossref","unstructured":"YanZ LiX LiM ZuoW ShanS.Shift\u2010net: image inpainting via deep feature rearrangement. Paper presented at: Proceedings of the European Conference on Computer Vision (ECCV) 1\u201317.2018.","DOI":"10.1007\/978-3-030-01264-9_1"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"YangC LuX LinZ ShechtmanE WangO LiH.High\u2010resolution image inpainting using multi\u2010scale neural patch synthesis. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 6721\u20136729.2017.","DOI":"10.1109\/CVPR.2017.434"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"YehRA ChenC Yian LimT SchwingAG Hasegawa\u2010JohnsonM DoMN.Semantic image inpainting with deep generative models. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 5485\u20135493.2017.","DOI":"10.1109\/CVPR.2017.728"},{"key":"e_1_2_8_27_1","doi-asserted-by":"crossref","unstructured":"YuJ LinZ YangJ ShenX LuX HuangTS.Generative image inpainting with contextual attention. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 5505\u20135514.2018.","DOI":"10.1109\/CVPR.2018.00577"},{"key":"e_1_2_8_28_1","doi-asserted-by":"crossref","unstructured":"RombachR BlattmannA LorenzD et al.High\u2010Resolution Image Synthesis with Latent Diffusion Models. Paper presented at: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022: 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_2_8_29_1","unstructured":"GregorK DanihelkaI GravesA RezendeDJ WierstraD.Draw: A recurrent neural network for image generation. arXiv preprint arXiv:1502.04623.2015."},{"key":"e_1_2_8_30_1","unstructured":"XuK BaJ KirosR et al.Show attend and tell: neural image caption generation with visual attention. Paper presented at: International Conference on Machine Learning 2048\u20132057.2015."},{"key":"e_1_2_8_31_1","doi-asserted-by":"crossref","unstructured":"YangZ HeX GaoJ DengL SmolaA.Stacked attention networks for image question answering. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 21\u201329.2016.","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_2_8_32_1","doi-asserted-by":"crossref","unstructured":"LinG ShenC Van Den HengelA ReidI.Efficient piecewise training of deep structured models for semantic segmentation. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 3194\u20133203.2016.","DOI":"10.1109\/CVPR.2016.348"},{"key":"e_1_2_8_33_1","doi-asserted-by":"crossref","unstructured":"ShenT ZhouT LongG JiangJ PanS ZhangC.Disan: Directional self\u2010attention network for rnn\/cnn\u2010free language understanding. Paper presented at: Thirty\u2010Second AAAI Conference on Artificial Intelligence.2018.","DOI":"10.1609\/aaai.v32i1.11941"},{"key":"e_1_2_8_34_1","unstructured":"VaswaniA ShazeerN ParmarN et al.Attention is all you need. Paper presented at: Advances in Neural Information Processing Systems 5998\u20136008.2017."},{"key":"e_1_2_8_35_1","doi-asserted-by":"crossref","unstructured":"WangX GirshickR GuptaA HeK.Non\u2010local neural networks. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 7794\u20137803.2018.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_2_8_36_1","unstructured":"ParmarN VaswaniA UszkoreitJ et al.Image transformer. arXiv preprint arXiv:1802.05751.2018."},{"key":"e_1_2_8_37_1","doi-asserted-by":"crossref","unstructured":"ZhaoL MoQ LinS et al.Uctgan: Diverse image in painting based on unsupervised cross\u2010space translation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2020:5741\u20105750.","DOI":"10.1109\/CVPR42600.2020.00578"},{"key":"e_1_2_8_38_1","article-title":"TeSTNeRF: Text\u2010Driven 3D Style Transfer via Cross\u2010Modal Learning","author":"Chen J","year":"2023","journal-title":"IJCAI"},{"key":"e_1_2_8_39_1","doi-asserted-by":"crossref","unstructured":"Wang Z ZhaoL ZuoZ et al. MicroAST: Towards super\u2010fast ultra\u2010resolution arbitrary style transfer.In Proceedings of the AAAI Conference on Artificial Intelligence 2023;37(3):2742\u20102750.","DOI":"10.1609\/aaai.v37i3.25374"},{"key":"e_1_2_8_40_1","doi-asserted-by":"crossref","unstructured":"ChenH ZhaoL WangZ et al.Dualast: Dual style\u2010learning networks for artistic style transfer. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2021:872\u2010881.","DOI":"10.1109\/CVPR46437.2021.00093"},{"key":"e_1_2_8_41_1","first-page":"7677","article-title":"StyleDiffusion: Controllable disentangled style transfer via diffusion models[C]\/\/Proceedings of the IEEE\/CVF","author":"Wang Z","year":"2023","journal-title":"International Conference on Computer Vision."},{"key":"e_1_2_8_42_1","first-page":"26561","article-title":"Artistic style transfer with internal\u2010external learning and contrastive learning","volume":"34","author":"Chen H","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_43_1","doi-asserted-by":"crossref","unstructured":"WangZ ZhaoL ChenH et al.Diversified arbitrary style transfer via deep feature perturbation[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2020:7789\u20107798.","DOI":"10.1109\/CVPR42600.2020.00781"},{"key":"e_1_2_8_44_1","doi-asserted-by":"crossref","unstructured":"JohnsonJ AlahiA Fei\u2010FeiL.Perceptual losses for real\u2010time style transfer and super\u2010resolution. Paper presented at: European Conference on Computer Vision 694\u2013711. Springer.2016.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_2_8_45_1","doi-asserted-by":"crossref","unstructured":"LiC WandM.Combining markov random fields and convolutional neural networks for image synthesis. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2479\u20132486.2016.","DOI":"10.1109\/CVPR.2016.272"},{"key":"e_1_2_8_46_1","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"Ba J","year":"2014","journal-title":"Adv Neur Inform Process Syst"},{"key":"e_1_2_8_47_1","doi-asserted-by":"crossref","unstructured":"Bucilua\u02c7C CaruanaR Niculescu\u2010MizilA.Model compression. Paper presented at: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 535\u2013541.2006.","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_2_8_48_1","unstructured":"HintonG VinyalsO DeanJ.Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.2015."},{"key":"e_1_2_8_49_1","unstructured":"ZagoruykoS KomodakisN.Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928.2016."},{"key":"e_1_2_8_50_1","doi-asserted-by":"crossref","unstructured":"ZhangY XiangT HospedalesTM LuH.Deep mutual learning. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 4320\u20134328.2018.","DOI":"10.1109\/CVPR.2018.00454"},{"key":"e_1_2_8_51_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: convolutional networks for biomedical image segmentation. Paper presented at: International Conference on Medical Image Computing and Computer\u2010Assisted Intervention 234\u2013241. Springer.2015.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_8_52_1","first-page":"658","article-title":"Generating images with perceptual similarity metrics based on deep networks","author":"Dosovitskiy A","year":"2016","journal-title":"Adv Neur Inform Process Syst"},{"key":"e_1_2_8_53_1","doi-asserted-by":"crossref","unstructured":"LinT\u2010Y Dolla'RP GirshickR HeK HariharanB BelongieS.Feature pyramid networks for object detection. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2117\u20132125.2017.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_8_54_1","first-page":"5767","article-title":"Improved training of wasserstein gans","author":"Gulrajani I","year":"2017","journal-title":"Adv Neur Inform Process Syst"},{"key":"e_1_2_8_55_1","doi-asserted-by":"crossref","unstructured":"RenY YuX ZhangR LiTH LiuS LiG.StructureFlow: image Inpainting via structure\u2010aware appearance flow. Paper presented at: Proceedings of the IEEE International Conference on Computer Vision 181\u2013190.2019.","DOI":"10.1109\/ICCV.2019.00027"},{"key":"e_1_2_8_56_1","unstructured":"SalimansT GoodfellowI ZarembaW CheungV Rad\u2010FordA ChenX.Improved techniques for training gans. Paper presented at: Advances in Neural Information Processing Systems 2234\u20132242.2016."}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.7960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T07:24:32Z","timestamp":1713252272000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.7960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":55,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["10.1002\/cpe.7960"],"URL":"https:\/\/doi.org\/10.1002\/cpe.7960","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"type":"print","value":"1532-0626"},{"type":"electronic","value":"1532-0634"}],"subject":[],"published":{"date-parts":[[2023,12,13]]},"assertion":[{"value":"2022-10-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-02","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e7960"}}