{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T09:16:17Z","timestamp":1773047777462,"version":"3.50.1"},"reference-count":38,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":67,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100007834","name":"Natural Science Foundation of Ningbo Municipality","doi-asserted-by":"publisher","award":["20251JCGY010084"],"award-info":[{"award-number":["20251JCGY010084"]}],"id":[{"id":"10.13039\/100007834","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Image inpainting aims to restore missing regions in a visually plausible and semantically coherent manner. Despite notable advances, existing deep learning approaches still face key limitations, including heavy Transformer\u2010based or unstable generative architectures, diffusion models with high computational cost, training pipelines that overlook the heterogeneous difficulty of diverse mask patterns, and the absence of explicit mechanisms to ensure smooth transitions along mask boundaries\u2014the most perceptually sensitive area in the reconstruction process. To address these challenges, we introduce CA\u2010Fill, a lightweight two\u2010stage encoder\u2013decoder framework that efficiently balances global structure recovery and fine\u2010grained texture refinement. By jointly integrating structural perceptual progression and optimization progression, the proposed method realizes a dual\u2010progressive perceptual alignment strategy that explicitly emphasizes boundary transition regions while progressively aligning training difficulty with model learning capacity. This design enables smoother boundary transitions, improved structural consistency, and enhanced perceptual realism under a lightweight computational budget. Extensive experiments on public benchmarks demonstrate that CA\u2010Fill achieves competitive or superior performance compared with representative baselines across both pixel\u2010level and perceptual evaluation metrics, while maintaining low parameter count and inference\u00a0cost.<\/jats:p>","DOI":"10.1049\/ipr2.70320","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T08:18:24Z","timestamp":1773044304000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual\u2010Progressive Perceptual Alignment for Lightweight Image Inpainting"],"prefix":"10.1049","volume":"20","author":[{"given":"Zhengtao","family":"Xiang","sequence":"first","affiliation":[{"name":"School of Intelligent and Connected Vehicle Hubei University of Automotive Technology Shiyan Hubei China"},{"name":"Air\u2010Ground Crowd Cooperation Key Shiyan Laboratory Hubei University of Automotive Technology Shiyan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4025-6348","authenticated-orcid":false,"given":"Yifan","family":"Du","sequence":"additional","affiliation":[{"name":"School of Intelligent and Connected Vehicle Hubei University of Automotive Technology Shiyan Hubei China"},{"name":"School of Computer and Data Engineering NingboTech University Ningbo Zhejiang Province P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufeng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Intelligent and Connected Vehicle Hubei University of Automotive Technology Shiyan Hubei China"},{"name":"Air\u2010Ground Crowd Cooperation Key Shiyan Laboratory Hubei University of Automotive Technology Shiyan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer and Data Engineering NingboTech University Ningbo Zhejiang Province P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"issue":"9","key":"e_1_2_11_2_1","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/TIP.2004.833105","article-title":"Region Filling and Object Removal by Exemplar\u2010Based Image Inpainting","volume":"13","author":"Criminisi A.","year":"2004","journal-title":"IEEE Transactions on Image Processing"},{"issue":"7","key":"e_1_2_11_3_1","doi-asserted-by":"crossref","first-page":"7775","DOI":"10.1609\/aaai.v38i7.28612","article-title":"Text Image Inpainting via Global Structure\u2010Guided Diffusion Models","volume":"8","author":"Zhu S.","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_2_11_4_1","doi-asserted-by":"crossref","first-page":"8811","DOI":"10.1109\/TMM.2024.3382484","article-title":"MMGInpainting: Multi\u2010Modality Guided Image Inpainting Based on Diffusion Models","volume":"26","author":"Zhang C.","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_2_11_5_1","doi-asserted-by":"crossref","unstructured":"A.Lugmayr M.Danelljan A.Romero F.Yu R.Timofte andL.Van Gool \u201cRepaint: Inpainting Using Denoising Diffusion Probabilistic Models \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2022) 11461\u201311471.","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_2_11_6_1","doi-asserted-by":"crossref","unstructured":"J.Peng D.Liu S.Xu andH.Li \u201cGenerating Diverse Structure for Image Inpainting With Hierarchical VQ\u2010VAE \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2021) 10775\u201310784.","DOI":"10.1109\/CVPR46437.2021.01063"},{"issue":"10","key":"e_1_2_11_7_1","doi-asserted-by":"crossref","first-page":"1852","DOI":"10.3390\/electronics13101852","article-title":"Hierarchical Vector\u2010Quantized Variational Autoencoder and Vector Credibility Mechanism for High\u2010Quality Image Inpainting","volume":"13","author":"Li C.","year":"2024","journal-title":"Electronics"},{"key":"e_1_2_11_8_1","unstructured":"K.Nazeri E.Ng T.Joseph F. Z.Qureshi andM.Ebrahimi \u201cEdgeConnect: Generative Image Inpainting With Adversarial Edge Learning \u201d preprint arXiv:1901.00212 January 1 2019 https:\/\/doi.org\/10.48550\/arXiv.1901.00212."},{"key":"e_1_2_11_9_1","doi-asserted-by":"crossref","unstructured":"H.Liu B.Jiang Y.Song W.Huang andC.Yang \u201cRethinking Image Inpainting via a Mutual Encoder\u2010Decoder With Feature Equalizations \u201d inProceedings of the 16th European Conference on Computer Vision\u2013ECCV 2020(Springer 2020) 725\u2013741.","DOI":"10.1007\/978-3-030-58536-5_43"},{"key":"e_1_2_11_10_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.111748","article-title":"Image Inpainting Based on GAN\u2010Driven Structure\u2010and Texture\u2010Aware Learning With Application to Object Removal","volume":"161","author":"Yeh C.\u2010H.","year":"2024","journal-title":"Applied Soft Computing"},{"key":"e_1_2_11_11_1","doi-asserted-by":"crossref","unstructured":"Y.Weng S.Ding andT.Zhou \u201cA Survey on Improved GAN Based Image Inpainting \u201d in2022 2nd International Conference on Consumer Electronics and Computer Engineering (ICCECE)(IEEE 2022) 319\u2013322.","DOI":"10.1109\/ICCECE54139.2022.9712740"},{"issue":"8","key":"e_1_2_11_12_1","doi-asserted-by":"crossref","first-page":"5788","DOI":"10.1007\/s11263-025-02448-w","article-title":"High\u2010Fidelity Image Inpainting With Multimodal Guided GAN Inversion","volume":"133","author":"Zhang L.","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"e_1_2_11_13_1","doi-asserted-by":"crossref","unstructured":"A.MohodandP. P.Nair \u201cA Novel Approach for Image Inpainting Using GAN \u201d in2025 6th International Conference on Control Communication and Computing (ICCC)(IEEE 2025) 1\u20137.","DOI":"10.1109\/ICCC64910.2025.11077276"},{"key":"e_1_2_11_14_1","doi-asserted-by":"crossref","unstructured":"L.Zhao Q.Mo S.Lin et\u00a0al. \u201cUCTGAN: Diverse Image Inpainting Based on Unsupervised Cross\u2010Space Translation \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2020) 5740\u20135749.","DOI":"10.1109\/CVPR42600.2020.00578"},{"key":"e_1_2_11_15_1","unstructured":"D. P.KingmaandM.Welling \u201cAuto\u2010Encoding Variational Bayes \u201d preprint arXiv:1312.6114 December 20 2013 https:\/\/doi.org\/10.48550\/arXiv.1312.6114."},{"key":"e_1_2_11_16_1","doi-asserted-by":"crossref","unstructured":"O.Avrahami D.Lischinski andO.Fried \u201cBlended Diffusion for Text\u2010Driven Editing of Natural Images \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(ACM 2022) 18187\u201318197.","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"e_1_2_11_17_1","doi-asserted-by":"crossref","unstructured":"R.Rombach A.Blattmann D.Lorenz P.Esser andB.Ommer \u201cHigh\u2010Resolution Image Synthesis With Latent Diffusion Models \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2022) 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","unstructured":"C.Saharia W.Chan H.Chang C.Lee J.Ho T.Salimans D. J.Fleet andM.Norouzi \u201cPalette: Image\u2010to\u2010Image Diffusion Models \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2022) 19723\u201319732.","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_2_11_19_1","doi-asserted-by":"crossref","unstructured":"W.Li Z.Lin K.Zhou L.Qi Y.Wang andJ.Jia \u201cMAT: Mask\u2010Aware Transformer for Large Hole Image Inpainting \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2022) 10758\u201310768.","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"e_1_2_11_20_1","doi-asserted-by":"crossref","unstructured":"J.Hu L.Shen andG.Sun \u201cSqueeze\u2010and\u2010Excitation Networks \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(IEEE 2018) 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"3","key":"e_1_2_11_21_1","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1145\/1531326.1531330","article-title":"Patchmatch: A Randomized Correspondence Algorithm for Structural Image Editing","volume":"28","author":"Barnes C.","year":"2009","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_2_11_22_1","doi-asserted-by":"crossref","unstructured":"D.Pathak P.Krahenbuhl J.Donahue T.Darrell andA. A.Efros \u201cContext Encoders: Feature Learning by Inpainting \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(IEEE 2016) 2536\u20132544.","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_2_11_23_1","unstructured":"G.Liu K. J.Shih T.\u2010C.Wang et\u00a0al. \u201cPartial Convolution Based Padding \u201d preprint arXiv:1811.11718 November 28 2018 https:\/\/doi.org\/10.48550\/arXiv.1811.11718."},{"key":"e_1_2_11_24_1","doi-asserted-by":"crossref","unstructured":"J.Yu Z.Lin J.Yang X.Shen X.Lu andT. S.Huang \u201cFree\u2010Form Image Inpainting With Gated Convolution \u201d inProceedings of the IEEE\/CVF International Conference on Computer Vision(IEEE 2019) 4471\u20134480.","DOI":"10.1109\/ICCV.2019.00457"},{"key":"e_1_2_11_25_1","doi-asserted-by":"crossref","unstructured":"X.Cheng Z.Fu andJ.Yang \u201cMulti\u2010Scale Dynamic Feature Encoding Network for Image Demoir\u00e9ing \u201d in2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW)(IEEE 2019) 3486\u20133493.","DOI":"10.1109\/ICCVW.2019.00432"},{"key":"e_1_2_11_26_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.107970","article-title":"Improved Multi\u2010Scale Dynamic Feature Encoding Network for Image Demoir\u00e9ing","volume":"116","author":"Cheng X.","year":"2021","journal-title":"Pattern Recognition"},{"key":"e_1_2_11_27_1","doi-asserted-by":"crossref","unstructured":"K.Nazeri E.Ng T.Joseph andF. Z.Qureshi \u201cEdgeconnect: Generative Image Inpainting With Adversarial Edge Learning \u201d inProceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)(IEEE 2019) 3265\u20133274.","DOI":"10.1109\/ICCVW.2019.00408"},{"key":"e_1_2_11_28_1","doi-asserted-by":"crossref","unstructured":"S.Woo J.Park J.\u2010Y.Lee andI. S.Kweon \u201cCBAM: Convolutional Block Attention Module \u201d inProceedings of the European Conference on Computer Vision (ECCV)(Springer 2018) 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_11_29_1","doi-asserted-by":"crossref","unstructured":"A.Lugmayr M.Danelljan A.Romero F.Yu R.Timofte andL.Van Gool \u201cRepaint: Inpainting Using Denoising Diffusion Probabilistic Models \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2022) 11461\u201311471.","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_2_11_30_1","unstructured":"T.Karras T.Aila S.Laine andJ.Lehtinen \u201cProgressive Growing of GANs for Improved Quality Stability and Variation \u201d preprint arXiv:1710.10196 October 27 2017 https:\/\/doi.org\/10.48550\/arXiv.1710.10196."},{"key":"e_1_2_11_31_1","doi-asserted-by":"crossref","unstructured":"D.Pathak P.Krahenbuhl J.Donahue T.Darrell andA. A.Efros \u201cContext Encoders: Feature Learning by Inpainting \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(IEEE 2016) 2536\u20132544.","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_2_11_32_1","doi-asserted-by":"crossref","unstructured":"J.Yu Z.Lin J.Yang X.Shen X.Lu andT. S.Huang \u201cFree\u2010Form Image Inpainting With Gated Convolution \u201d inProceedings of the IEEE\/CVF International Conference on Computer Vision(IEEE 2019) 4471\u20134480.","DOI":"10.1109\/ICCV.2019.00457"},{"key":"e_1_2_11_33_1","doi-asserted-by":"crossref","unstructured":"Z.Wan J.Zhang D.Chen andJ.Liao \u201cHigh\u2010Fidelity Pluralistic Image Completion With Transformers \u201d inProceedings of the IEEE\/CVF International Conference on Computer Vision(IEEE 2021) 4692\u20134701.","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"e_1_2_11_34_1","doi-asserted-by":"crossref","unstructured":"C.Zheng T.\u2010J.Cham andJ.Cai \u201cPluralistic Image Completion \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2019) 1438\u20131447.","DOI":"10.1109\/CVPR.2019.00153"},{"key":"e_1_2_11_35_1","first-page":"6629","volume-title":"Advances in Neural Information Processing Systems","author":"Heusel M.","year":"2017"},{"issue":"4","key":"e_1_2_11_36_1","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image Quality Assessment: From Error Visibility to Structural Similarity","volume":"13","author":"Wang Z.","year":"2004","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_2_11_37_1","doi-asserted-by":"crossref","unstructured":"Q.Wang B.Wu P.Zhu P.Li W.Zuo andQ.Hu \u201cECA\u2010Net: Efficient Channel Attention for Deep Convolutional Neural Networks \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2020) 11534\u201311542.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_2_11_38_1","doi-asserted-by":"crossref","unstructured":"D.Misra T.Nalamada A.Arora A.Blumer andQ.Qiu \u201cRotate to Attend: Convolutional Triplet Attention Module \u201d inProceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)(IEEE 2021) 3139\u20133148.","DOI":"10.1109\/WACV48630.2021.00318"},{"issue":"1","key":"e_1_2_11_39_1","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1080\/10867651.2004.10487596","article-title":"An image inpainting technique based on the fast marching method","volume":"9","author":"Telea A. C.","year":"2004","journal-title":"Journal of Graphics, GPU, & Game Tools"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70320","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70320","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T08:18:36Z","timestamp":1773044316000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70320"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/ipr2.70320"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70320","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-11-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70320"}}