{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:19:43Z","timestamp":1781713183775,"version":"3.54.5"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733963","type":"print"},{"value":"9783031733970","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73397-0_24","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:04:49Z","timestamp":1730574289000},"page":"412-428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["RealViformer: Investigating Attention for\u00a0Real-World Video Super-Resolution"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5017-0097","authenticated-orcid":false,"given":"Yuehan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-6141","authenticated-orcid":false,"given":"Angela","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"24_CR1","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VicReg: variance-invariance-covariance regularization for self-supervised learning. arXiv preprint arXiv:2105.04906 (2021)"},{"key":"24_CR2","unstructured":"Cao, J., Li, Y., Zhang, K., Van\u00a0Gool, L.: Video super-resolution transformer. arXiv preprint arXiv:2106.06847 (2021)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Wang, X., Yu, K., Dong, C., Loy, C.C.: BasicVSR: the search for essential components in video super-resolution and beyond. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4947\u20134956 (2021)","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"24_CR4","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5972\u20135981 (2022)","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Zhou, S., Xu, X., Loy, C.C.: Investigating tradeoffs in real-world video super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5962\u20135971 (2022)","DOI":"10.1109\/CVPR52688.2022.00587"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Pre-trained image processing transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299\u201312310 (2021)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, X., Zhou, J., Qiao, Y., Dong, C.: Activating more pixels in image super-resolution transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22367\u201322377 (2023)","DOI":"10.1109\/CVPR52729.2023.02142"},{"key":"24_CR8","unstructured":"Cogswell, M., Ahmed, F., Girshick, R., Zitnick, L., Batra, D.: Reducing overfitting in deep networks by decorrelating representations. arXiv preprint arXiv:1511.06068 (2015)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Dai, T., Cai, J., Zhang, Y., Xia, S.T., Zhang, L.: Second-order attention network for single image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11065\u201311074 (2019)","DOI":"10.1109\/CVPR.2019.01132"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Fuoli, D., Gu, S., Timofte, R.: Efficient video super-resolution through recurrent latent space propagation. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 3476\u20133485. IEEE (2019)","DOI":"10.1109\/ICCVW.2019.00431"},{"issue":"11","key":"24_CR11","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Hua, T., Wang, W., Xue, Z., Ren, S., Wang, Y., Zhao, H.: On feature decorrelation in self-supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9598\u20139608 (2021)","DOI":"10.1109\/ICCV48922.2021.00946"},{"key":"24_CR14","first-page":"5632","volume":"33","author":"Y Huang","year":"2020","unstructured":"Huang, Y., Li, S., Wang, L., Tan, T., et al.: Unfolding the alternating optimization for blind super resolution. Adv. Neural. Inf. Process. Syst. 33, 5632\u20135643 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1007\/978-3-030-58610-2_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Isobe","year":"2020","unstructured":"Isobe, T., Jia, X., Gu, S., Li, S., Wang, S., Tian, Q.: Video super-resolution with recurrent structure-detail network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 645\u2013660. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_38"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Jeelani, M., Cheema, N., Illgner-Fehns, K., Slusallek, P., Jaiswal, S., et\u00a0al.: Expanding synthetic real-world degradations for blind video super resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1199\u20131208 (2023)","DOI":"10.1109\/CVPRW59228.2023.00127"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Ji, X., Cao, Y., Tai, Y., Wang, C., Li, J., Huang, F.: Real-world super-resolution via kernel estimation and noise injection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 466\u2013467 (2020)","DOI":"10.1109\/CVPRW50498.2020.00241"},{"key":"24_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part II 14. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"issue":"11","key":"24_CR19","doi-asserted-by":"publisher","first-page":"2599","DOI":"10.1109\/TPAMI.2018.2865304","volume":"41","author":"WS Lai","year":"2018","unstructured":"Lai, W.S., Huang, J.B., Ahuja, N., Yang, M.H.: Fast and accurate image super-resolution with deep Laplacian pyramid networks. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2599\u20132613 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR20","unstructured":"Liang, J., et al.: VRT: a video restoration transformer. arXiv preprint arXiv:2201.12288 (2022)"},{"key":"24_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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1833\u20131844 (2021)","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"24_CR22","first-page":"378","volume":"35","author":"J Liang","year":"2022","unstructured":"Liang, J., et al.: Recurrent video restoration transformer with guided deformable attention. Adv. Neural. Inf. Process. Syst. 35, 378\u2013393 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"24_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.12.009","volume":"158","author":"C Ma","year":"2017","unstructured":"Ma, C., Yang, C.Y., Yang, X., Yang, M.H.: Learning a no-reference quality metric for single-image super-resolution. Comput. Vis. Image Underst. 158, 1\u201316 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Mei, Y., Fan, Y., Zhou, Y.: Image super-resolution with non-local sparse attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3517\u20133526 (2021)","DOI":"10.1109\/CVPR46437.2021.00352"},{"issue":"3","key":"24_CR26","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","volume":"20","author":"A Mittal","year":"2012","unstructured":"Mittal, A., Soundararajan, R., Bovik, A.C.: Making a \u201ccompletely blind\u2019\u2019 image quality analyzer. IEEE Sig. Process. Lett. 20(3), 209\u2013212 (2012)","journal-title":"IEEE Sig. Process. Lett."},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Nah, S., et al.: NTIRE 2019 challenge on video deblurring and super-resolution: dataset and study. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. (2019)","DOI":"10.1109\/CVPRW.2019.00251"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Pan, J., Bai, H., Dong, J., Zhang, J., Tang, J.: Deep blind video super-resolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4811\u20134820 (2021)","DOI":"10.1109\/ICCV48922.2021.00477"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4161\u20134170 (2017)","DOI":"10.1109\/CVPR.2017.291"},{"key":"24_CR30","unstructured":"Shi, S., Gu, J., Xie, L., Wang, X., Yang, Y., Dong, C.: Rethinking alignment in video super-resolution transformers. arXiv preprint arXiv:2207.08494 (2022)"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Song, Y., Wang, M., Yang, Z., Xian, X., Shi, Y.: NegVSR: augmenting negatives for generalized noise modeling in real-world video super-resolution. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 10705\u201310713 (2024)","DOI":"10.1609\/aaai.v38i9.28942"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Wang, H., Chen, X., Ni, B., Liu, Y., Liu, J.: Omni aggregation networks for lightweight image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22378\u201322387 (2023)","DOI":"10.1109\/CVPR52729.2023.02143"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Chan, K.C., Yu, K., Dong, C., Change\u00a0Loy, C.: EDVR: video restoration with enhanced deformable convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Xie, L., Dong, C., Shan, Y.: Real-ESRGAN: training real-world blind super-resolution with pure synthetic data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1905\u20131914 (2021)","DOI":"10.1109\/ICCVW54120.2021.00217"},{"issue":"4","key":"24_CR35","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","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(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Xie, L., Wang, X., Shi, S., Gu, J., Dong, C., Shan, Y.: Mitigating artifacts in real-world video super-resolution models. arXiv preprint arXiv:2212.07339 (2022)","DOI":"10.1609\/aaai.v37i3.25398"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Yang, X., Xiang, W., Zeng, H., Zhang, L.: Real-world video super-resolution: a benchmark dataset and a decomposition based learning scheme. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4781\u20134790 (2021)","DOI":"10.1109\/ICCV48922.2021.00474"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Yi, P., Wang, Z., Jiang, K., Jiang, J., Ma, J.: Progressive fusion video super-resolution network via exploiting non-local spatio-temporal correlations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3106\u20133115 (2019)","DOI":"10.1109\/ICCV.2019.00320"},{"key":"24_CR39","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5728\u20135739 (2022)","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, K., Liang, J., Van\u00a0Gool, L., Timofte, R.: Designing a practical degradation model for deep blind image super-resolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4791\u20134800 (2021)","DOI":"10.1109\/ICCV48922.2021.00475"},{"issue":"8","key":"24_CR41","doi-asserted-by":"publisher","first-page":"2579","DOI":"10.1109\/TIP.2015.2426416","volume":"24","author":"L Zhang","year":"2015","unstructured":"Zhang, L., Zhang, L., Bovik, A.C.: A feature-enriched completely blind image quality evaluator. IEEE Trans. Image Process. 24(8), 2579\u20132591 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR42","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. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"24_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/978-3-030-01234-2_18","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 294\u2013310. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_18"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73397-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:21:11Z","timestamp":1730575271000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73397-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733963","9783031733970"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73397-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}