{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:32:26Z","timestamp":1790832746777,"version":"4.1.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250620","type":"print"},{"value":"9783031250637","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25063-7_24","type":"book-chapter","created":{"date-parts":[[2023,2,15]],"date-time":"2023-02-15T20:10:15Z","timestamp":1676491815000},"page":"395-411","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Image Super-Resolution with\u00a0Deep Variational Autoencoders"],"prefix":"10.1007","author":[{"given":"Darius","family":"Chira","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilian","family":"Haralampiev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ole","family":"Winther","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Dittadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentin","family":"Li\u00e9vin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,16]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Timofte, R.: Ntire 2017 challenge on single image super-resolution: dataset and study. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (Jul 2017)","DOI":"10.1109\/CVPRW.2017.150"},{"key":"24_CR2","unstructured":"Bachlechner, T., Majumder, B.P., Mao, H.H., Cottrell, G.W., McAuley, J.: Rezero is all you need: Fast convergence at large depth. arXiv preprint arXiv:2003.04887 (2020)"},{"key":"24_CR3","doi-asserted-by":"publisher","unstructured":"Bevilacqua, M., Roumy, A., Guillemot, C., line Alberi Morel, M.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of the British Machine Vision Conference, pp. 135.1-135.10. BMVA Press (2012). https:\/\/doi.org\/10.5244\/C.26.135","DOI":"10.5244\/C.26.135"},{"key":"24_CR4","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"24_CR5","unstructured":"Chen, X., Mishra, N., Rohaninejad, M., Abbeel, P.: PixelSNAIL: an improved autoregressive generative model. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research. vol. 80, pp. 864\u2013872. PMLR (10\u201315 Jul 2018). https:\/\/proceedings.mlr.press\/v80\/chen18h.html"},{"key":"24_CR6","unstructured":"Child, R.: Very deep VAEs generalize autoregressive models and can outperform them on images. arXiv preprint arXiv:2011.10650 (2020)"},{"key":"24_CR7","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 (CVPR) (June 2019)","DOI":"10.1109\/CVPR.2019.01132"},{"key":"24_CR8","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. arXiv preprint arXiv:2105.05233 (2021)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Ding, K., Ma, K., Wang, S., Simoncelli, E.P.: Image quality assessment: unifying structure and texture similarity. arXiv preprint arXiv:2004.07728 (2020)","DOI":"10.1109\/TPAMI.2020.3045810"},{"issue":"2","key":"24_CR10","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2015","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295\u2013307 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Gatopoulos, I., Stol, M., Tomczak, J.M.: Super-resolution variational auto-encoders. arXiv preprint arXiv:2006.05218 (2020)","DOI":"10.3390\/e23060747"},{"key":"24_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems 27 (2014)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR14","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"47","key":"24_CR15","first-page":"1","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(47), 1\u201333 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Huang, J.B., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Jun 2015)","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"24_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-030-58592-1_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Hyun","year":"2020","unstructured":"Hyun, S., Heo, J.-P.: VarSR: variational super-resolution network for very low resolution images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 431\u2013447. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_26"},{"key":"24_CR18","unstructured":"Jolicoeur-Martineau, A.: The relativistic discriminator: a key element missing from standard GAN. arXiv preprint arXiv:1807.00734 (2018)"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"24_CR20","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"24_CR21","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"24_CR22","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: Generative flow with invertible 1x1 convolutions. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"24_CR23","unstructured":"Kingma, D.P., Salimans, T., Jozefowicz, R., Chen, X., Sutskever, I., Welling, M.: Improved variational inference with inverse autoregressive flow. In: Advances in Neural Information Processing Systems 29 (2016)"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,pp. 4681\u20134690 (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: SRDiff: single image super-resolution with diffusion probabilistic models. Neurocomputing 479, 47\u201359 (2022)","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., Mu Lee, K.: Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 136\u2013144 (2017)","DOI":"10.1109\/CVPRW.2017.151"},{"key":"24_CR27","doi-asserted-by":"publisher","unstructured":"Liu, J., Zhang, W., Tang, Y., Tang, J., Wu, G.: Residual feature aggregation network for image super-resolution. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2356\u20132365 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00243","DOI":"10.1109\/CVPR42600.2020.00243"},{"key":"24_CR28","unstructured":"Maal\u00f8e, L., Fraccaro, M., Li\u00e9vin, V., Winther, O.: BIVA: a very deep hierarchy of latent variables for generative modeling. arXiv preprint arXiv:1902.02102 (2019)"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001. vol. 2, pp. 416\u2013423 (2001)","DOI":"10.1109\/ICCV.2001.937655"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Matsui, Y., et al.: Sketch-based manga retrieval using manga109 dataset. Multimedia Tools Appl. 76(20), 21811\u201321838 (2016)","DOI":"10.1007\/s11042-016-4020-z"},{"key":"24_CR31","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 8162\u20138171. PMLR (18\u201324 Jul 2021). https:\/\/proceedings.mlr.press\/v139\/nichol21a.html"},{"key":"24_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-030-58610-2_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Niu","year":"2020","unstructured":"Niu, B., et al.: Single image super-resolution via a holistic attention network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 191\u2013207. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_12"},{"key":"24_CR33","unstructured":"van den Oord, A., Kalchbrenner, N., Espeholt, L., kavukcuoglu, k., Vinyals, O., Graves, A.: Conditional image generation with pixelCNN decoders. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol. 29. Curran Associates, Inc. (2016). https:\/\/proceedings.neurips.cc\/paper\/2016\/file\/b1301141feffabac455e1f90a7de2054-Paper.pdf"},{"key":"24_CR34","unstructured":"Oord, A.V., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of The 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 48, pp. 1747\u20131756. PMLR, New York, USA (20\u201322 Jun 2016). https:\/\/proceedings.mlr.press\/v48\/oord16.html"},{"key":"24_CR35","unstructured":"Parmar, N., et al.: Image transformer. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 4055\u20134064. PMLR (10\u201315 Jul 2018). https:\/\/proceedings.mlr.press\/v80\/parmar18a.html"},{"key":"24_CR36","unstructured":"Pisharoty, N., Jadhav, M., Dandawate, Y.: Performance evaluation of structural similarity index metric in different colorspaces for HVS based assessment of quality of colour images. Int. J. Eng. Technol. 5, 1555\u20131562 (2013)"},{"key":"24_CR37","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: International Conference on Machine Learning, pp. 1278\u20131286. PMLR (2014)"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S., Scholkopf, B., Hirsch, M.: EnhanceNet: single image super-resolution through automated texture synthesis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4491\u20134500 (2017)","DOI":"10.1109\/ICCV.2017.481"},{"key":"24_CR39","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol. 28. Curran Associates, Inc. (2015). https:\/\/proceedings.neurips.cc\/paper\/2015\/file\/8d55a249e6baa5c06772297520da2051-Paper.pdf"},{"key":"24_CR40","unstructured":"S\u00f8nderby, C.K., Raiko, T., Maal\u00f8e, L., S\u00f8nderby, S.K., Winther, O.: Ladder variational autoencoders. arXiv preprint arXiv:1602.02282 (2016)"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Tong, T., Li, G., Liu, X., Gao, Q.: Image super-resolution using dense skip connections. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4799\u20134807 (2017)","DOI":"10.1109\/ICCV.2017.514"},{"issue":"1","key":"24_CR42","first-page":"7184","volume":"17","author":"B Uria","year":"2016","unstructured":"Uria, B., C\u00f4t\u00e9, M.A., Gregor, K., Murray, I., Larochelle, H.: Neural autoregressive distribution estimation. J. Mach. Learn. Res. 17(1), 7184\u20137220 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"24_CR43","unstructured":"Vahdat, A., Kautz, J.: NVAE: a deep hierarchical variational autoencoder. arXiv preprint arXiv:2007.03898 (2020)"},{"key":"24_CR44","unstructured":"Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. In: Proceedings of the European conference on computer vision (ECCV) workshops, pp. 0\u20130 (2018)"},{"key":"24_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/978-3-642-27413-8_47","volume-title":"Curves and Surfaces","author":"R Zeyde","year":"2012","unstructured":"Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Boissonnat, J.-D. (ed.) Curves and Surfaces 2010. LNCS, vol. 6920, pp. 711\u2013730. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27413-8_47"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2472\u20132481 (2018)","DOI":"10.1109\/CVPR.2018.00262"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25063-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T09:55:28Z","timestamp":1728899728000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25063-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250620","9783031250637"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25063-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"16 February 2023","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}