{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:32:51Z","timestamp":1773772371907,"version":"3.50.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729942","type":"print"},{"value":"9783031729959","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"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\/978-3-031-72995-9_24","type":"book-chapter","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T19:17:31Z","timestamp":1732389451000},"page":"421-437","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Rethinking Video Deblurring with\u00a0Wavelet-Aware Dynamic Transformer and\u00a0Diffusion Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8059-3438","authenticated-orcid":false,"given":"Chen","family":"Rao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2938-527X","authenticated-orcid":false,"given":"Guangyuan","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7486-2103","authenticated-orcid":false,"given":"Zehua","family":"Lan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2894-9456","authenticated-orcid":false,"given":"Jiakai","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2902-8086","authenticated-orcid":false,"given":"Junsheng","family":"Luan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7994-6725","authenticated-orcid":false,"given":"Wei","family":"Xing","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4791-454X","authenticated-orcid":false,"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6313-5349","authenticated-orcid":false,"given":"Huaizhong","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Jianfeng","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Dalong","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"24_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S.W., Fidler, S., Kreis, K.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"24_CR3","unstructured":"Chan, K.C., Zhou, S., Xu, X., Loy, C.C.: On the generalization of basicvsr++ to video deblurring and denoising. arXiv preprint arXiv:2204.05308 (2022)"},{"key":"24_CR4","doi-asserted-by":"publisher","unstructured":"Chen, L., Chu, X., Zhang, X., Sun, J.: Simple baselines for image restoration. In: European Conference on Computer Vision, pp. 17\u201333. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20071-7_2","DOI":"10.1007\/978-3-031-20071-7_2"},{"key":"24_CR5","unstructured":"Chen, Z., et al.: Hierarchical integration diffusion model for realistic image deblurring. arXiv preprint arXiv:2305.12966 (2023)"},{"issue":"4","key":"24_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2185520.2185560","volume":"31","author":"S Cho","year":"2012","unstructured":"Cho, S., Wang, J., Lee, S.: Video deblurring for hand-held cameras using patch-based synthesis. ACM Trans. Graphics (TOG) 31(4), 1\u20139 (2012)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chu, T., et al.: Rethinking fast fourier convolution in image inpainting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23195\u201323205 (2023)","DOI":"10.1109\/ICCV51070.2023.02120"},{"key":"24_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7346\u20137356 (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Fan, Y., Hong, C., Wang, X., Zeng, Z., Guo, Z.: Multi-input-output fusion attention module for deblurring networks. In: 2021 IEEE International Conference on Big Data (Big Data), pp. 3176\u20133182. IEEE (2021)","DOI":"10.1109\/BigData52589.2021.9671844"},{"key":"24_CR11","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":"24_CR12","doi-asserted-by":"crossref","unstructured":"Huang, H., He, R., Sun, Z., Tan, T.: Wavelet-srnet: a wavelet-based CNN for multi-scale face super resolution. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1689\u20131697 (2017)","DOI":"10.1109\/ICCV.2017.187"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Hyun\u00a0Kim, T., Mu\u00a0Lee, K.: Generalized video deblurring for dynamic scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5426\u20135434 (2015)","DOI":"10.1109\/CVPR.2015.7299181"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Hyun\u00a0Kim, T., Mu\u00a0Lee, K., Scholkopf, B., Hirsch, M.: Online video deblurring via dynamic temporal blending network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4038\u20134047 (2017)","DOI":"10.1109\/ICCV.2017.435"},{"key":"24_CR15","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.neucom.2022.11.074","volume":"520","author":"A Li","year":"2023","unstructured":"Li, A., Zhao, L., Zuo, Z., Wang, Z., Xing, W., Lu, D.: Migt: multi-modal image inpainting guided with text. Neurocomputing 520, 376\u2013385 (2023)","journal-title":"Neurocomputing"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Li, D., et al.: Arvo: learning all-range volumetric correspondence for video deblurring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7721\u20137731 (2021)","DOI":"10.1109\/CVPR46437.2021.00763"},{"key":"24_CR17","doi-asserted-by":"publisher","unstructured":"Li, G., Lyu, J., Wang, C., Dou, Q., Qin, J.: Wavtrans: synergizing wavelet and cross-attention transformer for multi-contrast mri super-resolution. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 463\u2013473. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-16446-0_44","DOI":"10.1007\/978-3-031-16446-0_44"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Li, G., Rao, C., Mo, J., Zhang, Z., Xing, W., Zhao, L.: Rethinking diffusion model for multi-contrast mri super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11365\u201311374 (2024)","DOI":"10.1109\/CVPR52733.2024.01080"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, L., Lin, Z., Xu, D., Lu, D.: Non-local image inpainting using low-rank matrix completion. In: Computer Graphics Forum. vol.\u00a034, pp. 111\u2013122. Wiley Online Library (2015)","DOI":"10.1111\/cgf.12521"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, L., Xu, D., Lu, D.: Efficient image completion method based on alternating direction theory. In: 2013 IEEE International Conference on Image Processing, pp. 700\u2013703. IEEE (2013)","DOI":"10.1109\/ICIP.2013.6738144"},{"key":"24_CR21","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_CR22","unstructured":"Lin, J., et al.: Flow-guided sparse transformer for video deblurring. arXiv preprint arXiv:2201.01893 (2022)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: More control for free! image synthesis with semantic diffusion guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 289\u2013299 (2023)","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Videofusion: decomposed diffusion models for high-quality video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10209\u201310218 (2023)","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Nah, S., Hyun\u00a0Kim, T., Mu\u00a0Lee, K.: Deep multi-scale convolutional neural network for dynamic scene deblurring. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3883\u20133891 (2017)","DOI":"10.1109\/CVPR.2017.35"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Nah, S., Son, S., Lee, K.M.: Recurrent neural networks with intra-frame iterations for video deblurring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8102\u20138111 (2019)","DOI":"10.1109\/CVPR.2019.00829"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"\u00d6zdenizci, O., Legenstein, R.: Restoring vision in adverse weather conditions with patch-based denoising diffusion models. IEEE Trans. Patt. Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3238179"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Pan, J., Bai, H., Tang, J.: Cascaded deep video deblurring using temporal sharpness prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3043\u20133051 (2020)","DOI":"10.1109\/CVPR42600.2020.00311"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Pan, J., Xu, B., Dong, J., Ge, J., Tang, J.: Deep discriminative spatial and temporal network for efficient video deblurring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22191\u201322200 (2023)","DOI":"10.1109\/CVPR52729.2023.02125"},{"key":"24_CR30","unstructured":"Paszke, A., et\u00a0al.: Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inf. Proce. Syst. 32 (2019)"},{"key":"24_CR31","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":"24_CR32","doi-asserted-by":"crossref","unstructured":"Ruan, L., et al.: Mm-diffusion: Learning multi-modal diffusion models for joint audio and video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10219\u201310228 (2023)","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Su, S., Delbracio, M., Wang, J., Sapiro, G., Heidrich, W., Wang, O.: Deep video deblurring for hand-held cameras. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1279\u20131288 (2017)","DOI":"10.1109\/CVPR.2017.33"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Suin, M., Rajagopalan, A.: Gated spatio-temporal attention-guided video deblurring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7802\u20137811 (2021)","DOI":"10.1109\/CVPR46437.2021.00771"},{"key":"24_CR35","first-page":"24804","volume":"34","author":"Y Tashiro","year":"2021","unstructured":"Tashiro, Y., Song, J., Song, Y., Ermon, S.: Csdi: conditional score-based diffusion models for probabilistic time series imputation. Adv. Neural. Inf. Process. Syst. 34, 24804\u201324816 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR36","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_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., Li, H.: Uformer: a general u-shaped transformer for image restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17683\u201317693 (2022)","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Xia, B., et al.: Diffir: Efficient diffusion model for image restoration. arXiv preprint arXiv:2303.09472 (2023)","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"24_CR39","doi-asserted-by":"publisher","first-page":"8976","DOI":"10.1109\/TIP.2020.3023534","volume":"29","author":"X Xiang","year":"2020","unstructured":"Xiang, X., Wei, H., Pan, J.: Deep video deblurring using sharpness features from exemplars. IEEE Trans. Image Process. 29, 8976\u20138987 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Yu, S., Sohn, K., Kim, S., Shin, J.: Video probabilistic diffusion models in projected latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18456\u201318466 (2023)","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., et al.: Multi-stage progressive image restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14821\u201314831 (2021)","DOI":"10.1109\/CVPR46437.2021.01458"},{"issue":"1","key":"24_CR42","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/TIP.2018.2867733","volume":"28","author":"K Zhang","year":"2018","unstructured":"Zhang, K., Luo, W., Zhong, Y., Ma, L., Liu, W., Li, H.: Adversarial spatio-temporal learning for video deblurring. IEEE Trans. Image Process. 28(1), 291\u2013301 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Artbank: artistic style transfer with pre-trained diffusion model and implicit style prompt bank. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 7396\u20137404 (2024)","DOI":"10.1609\/aaai.v38i7.28570"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, L., et al.: Uctgan: diverse image inpainting based on unsupervised cross-space translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5741\u20135750 (2020)","DOI":"10.1109\/CVPR42600.2020.00578"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Zheng, B., Yuan, S., Slabaugh, G., Leonardis, A.: Image demoireing with learnable bandpass filters. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3636\u20133645 (2020)","DOI":"10.1109\/CVPR42600.2020.00369"},{"key":"24_CR46","doi-asserted-by":"publisher","unstructured":"Zhong, Z., Gao, Y., Zheng, Y., Zheng, B.: Efficient spatio-temporal recurrent neural network for video deblurring. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VI 16, pp. 191\u2013207. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_12","DOI":"10.1007\/978-3-030-58539-6_12"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, S., Zhang, J., Pan, J., Xie, H., Zuo, W., Ren, J.: Spatio-temporal filter adaptive network for video deblurring. In: Proceedings of the IEEE\/CVF International Conference On Computer Vision, pp. 2482\u20132491 (2019)","DOI":"10.1109\/ICCV.2019.00257"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Zuo, Z., et al.: Generative image inpainting with segmentation confusion adversarial training and contrastive learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a037, pp. 3888\u20133896 (2023)","DOI":"10.1609\/aaai.v37i3.25502"}],"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\/978-3-031-72995-9_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T20:06:36Z","timestamp":1732392396000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72995-9_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031729942","9783031729959"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72995-9_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 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"}}]}}