{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:51:38Z","timestamp":1780422698657,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620708","type":"print"},{"value":"9789819620715","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-2071-5_12","type":"book-chapter","created":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T15:34:58Z","timestamp":1735745698000},"page":"155-169","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["TDM: Temporally-Consistent Diffusion Model for\u00a0All-in-One Real-World Video Restoration"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7122-2087","authenticated-orcid":false,"given":"Yizhou","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3908-0517","authenticated-orcid":false,"given":"Zihua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6733-3406","authenticated-orcid":false,"given":"Yusuke","family":"Monno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5787-0742","authenticated-orcid":false,"given":"Masatoshi","family":"Okutomi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,2]]},"reference":[{"key":"12_CR1","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd gans. arXiv preprint arXiv:1801.01401 (2018)"},{"key":"12_CR2","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: Learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"12_CR4","unstructured":"Cao, J., et al.: Learning task-oriented flows to mutually guide feature alignment in synthesized and real video denoising. arXiv preprint arXiv:2208.11803 (2022)"},{"key":"12_CR5","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":"12_CR6","unstructured":"Chen, H., et al.: Robust classification via a single diffusion model. arXiv preprint arXiv:2305.15241 (2023)"},{"key":"12_CR7","unstructured":"Clark, K., Jaini, P.: Text-to-image diffusion models are zero shot classifiers. Adv. Neural Inform. Process. Syst. 36 (2024)"},{"key":"12_CR8","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Guan, Z., Xing, Q., Xu, M., Yang, R., Liu, T., Wang, Z.: Mfqe 2.0: a new approach for multi-frame quality enhancement on compressed video. IEEE Trans. Pattern Analy. Mach. Intell. 43(3), 949\u2013963 (2019)","DOI":"10.1109\/TPAMI.2019.2944806"},{"key":"12_CR10","unstructured":"Guo, Y., et al.: Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"12_CR11","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"12_CR12","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."},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2video-zero: Text-to-image diffusion models are zero-shot video generators. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15954\u201315964 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Rohrbach, A., Schiele, B.: Video object segmentation with language referring expressions. In: Asian Conference on Computer Vision, pp. 123\u2013141 (2019)","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Li, B., Liu, X., Hu, P., Wu, Z., Lv, J., Peng, X.: All-in-one image restoration for unknown corruption. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17452\u201317462 (2022)","DOI":"10.1109\/CVPR52688.2022.01693"},{"key":"12_CR17","unstructured":"Liang, J., et al.: Vrt: A video restoration transformer. arXiv preprint arXiv:2201.12288 (2022)"},{"key":"12_CR18","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":"12_CR19","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3d object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"12_CR20","unstructured":"Liu, Y., Lin, C., Zeng, Z., Long, X., Liu, L., Komura, T., Wang, W.: Syncdreamer: Generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, F., Ke, Z., Zhao, N., Lau, R.W.: Diff-plugin: Revitalizing details for diffusion-based low-level tasks. arXiv preprint arXiv:2403.00644 (2024)","DOI":"10.1109\/CVPR52733.2024.00402"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"12_CR23","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 (2019)","DOI":"10.1109\/CVPRW.2019.00251"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"\u00d6zdenizci, O., Legenstein, R.: Restoring vision in adverse weather conditions with patch-based denoising diffusion models. IEEE Trans. Pattern Anal. Mach. Intell.dd (2023)","DOI":"10.1109\/TPAMI.2023.3238179"},{"key":"12_CR25","unstructured":"Potlapalli, V., Zamir, S.W., Khan, S., Khan, F.S.: Promptir: prompting for all-in-one blind image restoration. arXiv preprint arXiv:2306.13090 (2023)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Ren, M., Delbracio, M., Talebi, H., Gerig, G., Milanfar, P.: Multiscale structure guided diffusion for image deblurring. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10721\u201310733 (2023)","DOI":"10.1109\/ICCV51070.2023.00984"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., Fleet, D., Norouzi, M.: Palette: Image-to-image diffusion models. In: Proceedings of ACM SIGGRAPH Conference, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"12_CR29","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Tassano, M., Delon, J., Veit, T.: Fastdvdnet: towards real-time deep video denoising without flow estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1354\u20131363 (2020)","DOI":"10.1109\/CVPR42600.2020.00143"},{"key":"12_CR31","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"12_CR33","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":"12_CR34","doi-asserted-by":"crossref","unstructured":"Yue, H., Cao, C., Liao, L., Chu, R., Yang, J.: Supervised raw video denoising with a benchmark dataset on dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2301\u20132310 (2020)","DOI":"10.1109\/CVPR42600.2020.00237"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Yue, Z., Xie, J., Zhao, Q., Meng, D.: Semi-supervised video deraining with dynamical rain generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 642\u2013652 (2021)","DOI":"10.1109\/CVPR46437.2021.00070"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Learning to restore hazy video: a new real-world dataset and a new method. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9239\u20139248 (2021)","DOI":"10.1109\/CVPR46437.2021.00912"},{"key":"12_CR38","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: Controlvideo: training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077 (2023)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2071-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T16:02:22Z","timestamp":1735747342000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2071-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620708","9789819620715"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2071-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}