{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:34:34Z","timestamp":1773002074652,"version":"3.50.1"},"reference-count":48,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101346"],"award-info":[{"award-number":["62101346"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301330"],"award-info":[{"award-number":["62301330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CAAI Trans on Intel Tech"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Although Transformer\u2010based image restoration methods have demonstrated impressive performance, existing Transformers still insufficiently exploit multiscale information. Previous non\u2010Transformer\u2010based studies have shown that incorporating multiscale features is crucial for improving restoration results. In this paper, we propose a multiscale Transformer (MST) that captures cross\u2010scale attention among tokens, thereby effectively leveraging the multiscale patch recurrence prior of natural images. Furthermore, we introduce a channel\u2010gate feed\u2010forward network (CGFN) to enhance inter\u2010channel information aggregation and reduce channel redundancy. To simultaneously utilise global, local and multiscale features, we design a multitype feature integration block (MFIB). Extensive experiments on both image super\u2010resolution and HEVC compressed video artefact reduction demonstrate that the proposed MST achieves state\u2010of\u2010the\u2010art performance. Ablation studies further verify the effectiveness of each proposed module.<\/jats:p>","DOI":"10.1049\/cit2.70079","type":"journal-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T13:29:16Z","timestamp":1763818156000},"page":"41-54","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi\u2010Scale Transformer for Image Restoration"],"prefix":"10.1049","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6819-0125","authenticated-orcid":false,"given":"Wuzhen","family":"Shi","sequence":"first","affiliation":[{"name":"Shenzhen Key Laboratory of Digital Creative Technology, Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering Shenzhen University  Shenzhen China"}]},{"given":"Youwei","family":"Pan","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Digital Creative Technology, Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering Shenzhen University  Shenzhen China"}]},{"given":"Chun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.  Beijing China"}]},{"given":"Yuqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.  Beijing China"}]},{"given":"Shaobo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.  Beijing China"}]},{"given":"Heng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.  Beijing China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6303-8178","authenticated-orcid":false,"given":"Yang","family":"Wen","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Digital Creative Technology, Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering Shenzhen University  Shenzhen China"}]}],"member":"265","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"e_1_2_10_2_1","first-page":"1","volume-title":"ICLR 2021\u20149th International Conference on Learning Representations","author":"Dosovitskiy A.","year":"2021"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_2_10_4_1","first-page":"22367","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen X.","year":"2023"},{"key":"e_1_2_10_5_1","first-page":"12312","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Chen Z.","year":"2023"},{"key":"e_1_2_10_6_1","first-page":"1","volume-title":"ICLR","author":"Zhang J.","year":"2023"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01753"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02468"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2007.901238"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459271"},{"key":"e_1_2_10_11_1","first-page":"10853","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ren S.","year":"2022"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12297"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12285"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12256"},{"key":"e_1_2_10_18_1","first-page":"4681","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Ledig C.","year":"2017"},{"key":"e_1_2_10_19_1","first-page":"1905","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wang X.","year":"2021"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01668"},{"key":"e_1_2_10_21_1","first-page":"2279","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Long W.","year":"2025"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2944806"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475710"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6697"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3214775"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2022.3147441"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00286"},{"key":"e_1_2_10_28_1","first-page":"945","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Michaeli T.","year":"2013"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"e_1_2_10_30_1","first-page":"1059","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Yang J.","year":"2013"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_10_34_1","unstructured":"D.HendrycksandK.Gimpel \u201cGaussian Error Linear Units (Gelus) \u201d preprint arXiv:1606.08415 (2016)."},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.149"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.135"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27413-8_47"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042\u2010016\u20104020\u2010z"},{"key":"e_1_2_10_41_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015","author":"Kingma D. P.","year":"2015"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3552086"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01132"},{"key":"e_1_2_10_44_1","first-page":"3499","article-title":"Cross\u2010Scale Internal Graph Neural Network for Image Super\u2010Resolution","volume":"33","author":"Zhou S.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_12"},{"key":"e_1_2_10_46_1","first-page":"3517","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Mei Y.","year":"2021"},{"key":"e_1_2_10_47_1","first-page":"1089","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)","author":"Li W.","year":"2023"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00276"},{"key":"e_1_2_10_49_1","first-page":"11963","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ding X.","year":"2022"}],"container-title":["CAAI Transactions on Intelligence Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70079","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cit2.70079","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:10:29Z","timestamp":1772993429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cit2.70079"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1049\/cit2.70079"],"URL":"https:\/\/doi.org\/10.1049\/cit2.70079","archive":["Portico"],"relation":{},"ISSN":["2468-6557","2468-2322"],"issn-type":[{"value":"2468-6557","type":"print"},{"value":"2468-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,22]]},"assertion":[{"value":"2025-06-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}