{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:50:09Z","timestamp":1767315009431,"version":"3.48.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032101846","type":"print"},{"value":"9783032101853","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-10185-3_48","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:47:12Z","timestamp":1767314832000},"page":"608-620","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Frame Alignment for\u00a0Video Super-Resolution Using Attention"],"prefix":"10.1007","author":[{"given":"Marco","family":"Di Rienzo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2017-1061","authenticated-orcid":false,"given":"Matteo","family":"Bruni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-9407","authenticated-orcid":false,"given":"Leonardo","family":"Galteri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2537-2700","authenticated-orcid":false,"given":"Federico","family":"Becattini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1364-218X","authenticated-orcid":false,"given":"Marco","family":"Bertini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"48_CR1","doi-asserted-by":"crossref","unstructured":"Agnolucci, L., Galteri, L., Bertini, M., Del\u00a0Bimbo, A.: Arniqa: learning distortion manifold for image quality assessment. In: Proc. of WACV (2024)","DOI":"10.1109\/WACV57701.2024.00026"},{"key":"48_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T.: A general and adaptive robust loss function (2019)","DOI":"10.1109\/CVPR.2019.00446"},{"key":"48_CR3","doi-asserted-by":"crossref","unstructured":"Caballero, J., et al.: Real-time video super-resolution with spatio-temporal networks and motion compensation. In: Proc. of CVPR, pp. 4778\u20134787 (2017)","DOI":"10.1109\/CVPR.2017.304"},{"key":"48_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Y., Wang, C., Song, C., Tang, Y., Li, H.: Real-time super-resolution system of 4k-video based on deep learning (2021)","DOI":"10.1109\/ASAP52443.2021.00019"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Chan, K.C.K., Wang, X., Yu, K., Dong, C., Loy, C.C.: Basicvsr: the search for essential components in video super-resolution and beyond (2021)","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"48_CR6","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Zhou, S., Xu, X., Loy, C.C.: Basicvsr++: improving video super-resolution with enhanced propagation and alignment. In: Proc. of CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"48_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Pre-trained image processing transformer. In: Proc. of CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"48_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, X., Zhou, J., Qiao, Y., Dong, C.: Activating more pixels in image super-resolution transformer. In: Proc. of CVPR, pp. 22367\u201322377 (2023)","DOI":"10.1109\/CVPR52729.2023.02142"},{"key":"48_CR9","first-page":"25478","volume":"35","author":"Z Chen","year":"2022","unstructured":"Chen, Z., Zhang, Y., Gu, J., Kong, L., Yuan, X., et al.: Cross aggregation transformer for image restoration. NeurIPS 35, 25478\u201325490 (2022)","journal-title":"NeurIPS"},{"key":"48_CR10","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks (2015)","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network (2016)","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"48_CR12","doi-asserted-by":"crossref","unstructured":"Galteri, L., Seidenari, L., Bertini, M., Bimbo, A.: Deep universal generative adversarial compression artifact removal. IEEE Trans. Multimedia 21 (2019)","DOI":"10.1109\/TMM.2019.2895280"},{"key":"48_CR13","doi-asserted-by":"crossref","unstructured":"Hor\u00e9, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition, pp. 2366\u20132369 (2010). https:\/\/api.semanticscholar.org\/CorpusID:9506273","DOI":"10.1109\/ICPR.2010.579"},{"key":"48_CR14","doi-asserted-by":"crossref","unstructured":"Kappeler, A., Yoo, S., Dai, Q., Katsaggelos, A.K.: Video super-resolution with convolutional neural networks. IEEE Trans. Comput. Imaging 2, 109\u2013122 (2016). https:\/\/api.semanticscholar.org\/CorpusID:9356783","DOI":"10.1109\/TCI.2016.2532323"},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks (2016)","DOI":"10.1109\/CVPR.2016.182"},{"key":"48_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017)"},{"key":"48_CR17","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84 \u2013 90 (2012). https:\/\/api.semanticscholar.org\/CorpusID:195908774","DOI":"10.1145\/3065386"},{"key":"48_CR18","doi-asserted-by":"crossref","unstructured":"Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"48_CR19","unstructured":"Li, Z., Aaron, A., Katsavounidis, I., Moorthy, A., Manohara, M.: Toward a practical perceptual video quality metric (2016). https:\/\/netflixtechblog.com"},{"key":"48_CR20","doi-asserted-by":"crossref","unstructured":"Liang, J., et al.: VRT: a video restoration transformer. IEEE Trans. Image Process. (2024)","DOI":"10.1109\/TIP.2024.3372454"},{"key":"48_CR21","doi-asserted-by":"crossref","unstructured":"Liang, J., Cao, J., Sun, G., Zhang, K., Van\u00a0Gool, L., Timofte, R.: Swinir: image restoration using swin transformer. In: Proc. of ICCV, pp. 1833\u20131844 (2021)","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"48_CR22","unstructured":"Liang, J., et al.: Recurrent video restoration transformer with guided deformable attention (2022)"},{"key":"48_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Video super resolution based on deep learning: a comprehensive survey (2022)","DOI":"10.1007\/s10462-022-10147-y"},{"key":"48_CR24","doi-asserted-by":"publisher","first-page":"3847","DOI":"10.1109\/TMM.2021.3108943","volume":"24","author":"D Ma","year":"2022","unstructured":"Ma, D., Zhang, F., Bull, D.R.: BVI-DVC: a training database for deep video compression. IEEE Trans. Multimedia 24, 3847\u20133858 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"48_CR25","doi-asserted-by":"crossref","unstructured":"Qing, T., Ying, X., Sha, Z., Wu, J.: Video super-resolution with pyramid flow-guided deformable alignment network. In: Proc. of ICEEMT. IEEE (2023)","DOI":"10.1109\/ICEEMT59522.2023.10263063"},{"key":"48_CR26","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network (2016)","DOI":"10.1109\/CVPR.2017.291"},{"key":"48_CR27","first-page":"36081","volume":"35","author":"S Shi","year":"2022","unstructured":"Shi, S., Gu, J., Xie, L., Wang, X., Yang, Y., Dong, C.: Rethinking alignment in video super-resolution transformers. NeurIPS 35, 36081\u201336093 (2022)","journal-title":"NeurIPS"},{"key":"48_CR28","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. Proc. CVPR (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"48_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"48_CR30","unstructured":"Tian, Y., Zhang, Y., Fu, Y., Xu, C.: TDAN: temporally deformable alignment network for video super-resolution (2018)"},{"key":"48_CR31","doi-asserted-by":"crossref","unstructured":"Wang, J., Shao, Z., Huang, X., Lu, T., Zhang, R., Li, Y.: From artifact removal to super-resolution. IEEE Trans. Geosci. Remote Sens. 60, 1\u201315 (2022)","DOI":"10.1109\/TGRS.2022.3196709"},{"key":"48_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., Chan, K.C.K., Yu, K., Dong, C., Loy, C.C.: Edvr: video restoration with enhanced deformable convolutional networks (2019)","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"48_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600\u2013612 (2004). https:\/\/api.semanticscholar.org\/CorpusID:207761262","DOI":"10.1109\/TIP.2003.819861"},{"key":"48_CR34","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Restormer: efficient transformer for high-resolution image restoration. In: Proc. of CVPR, pp. 5728\u20135739 (2022)","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"48_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"48_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Chen, F., Zhu, S., Liu, Y., Zhou, X., Xiong, R., Zeng, B.: Dvsrnet: deep video super-resolution based on progressive deformable alignment and temporal-sparse enhancement. IEEE Trans. Neural Netw. Learn. Syst. (2024)","DOI":"10.1109\/TNNLS.2023.3347450"},{"key":"48_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Li, P., Li, Q.: Attention retractable frequency fusion transformer for image super resolution. In: Proc. of CVPR, pp. 1756\u20131763 (2023)","DOI":"10.1109\/CVPRW59228.2023.00176"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10185-3_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:47:16Z","timestamp":1767314836000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10185-3_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032101846","9783032101853"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10185-3_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}