{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T19:11:54Z","timestamp":1773256314087,"version":"3.50.1"},"reference-count":65,"publisher":"Association for Computing Machinery (ACM)","issue":"8","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A20333, 62472443, 62376287"],"award-info":[{"award-number":["U24A20333, 62472443, 62376287"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004735","name":"Hunan Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["2024JJ3032, 2025JJ60409, 2025JJ70639"],"award-info":[{"award-number":["2024JJ3032, 2025JJ60409, 2025JJ70639"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Noncommunicable Chronic Diseases-National Science and Technology Major","award":["2023ZD0508200, 2023ZD0508201"],"award-info":[{"award-number":["2023ZD0508200, 2023ZD0508201"]}]},{"name":"Scientific Research Project of Hunan Provincial Department of Education","award":["24A0485"],"award-info":[{"award-number":["24A0485"]}]},{"name":"Hunan University of Arts and Science Doctoral Research Initiation","award":["22BSQD02"],"award-info":[{"award-number":["22BSQD02"]}]},{"name":"International Science and Technology Innovation Joint Base of Machine Vision and Medical Image Processing in Hunan Province","award":["2021CB1013"],"award-info":[{"award-number":["2021CB1013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:p>\n            Blind super-resolution (BSR) is entering a new era focused on diverse and complex applications, where the tradeoff between generalization and performance prevents models from performing as they should. Model performance decreases when trained on multiple degraded images due to the inter-class and intra-class imbalances in degradation prediction, which consists of degradation sampling and estimation. The inter-class imbalance in degradation estimation causes inaccurate estimates, leading to severe artifacts in images. The intra-class imbalance in degradation sampling causes a long-tail problem, leading to model collapse and satisfactory results only in specific applications. To tackle these challenges, we propose adaptive alignment contrastive learning (AACL), which includes adaptive degradation sampling (ADS) and\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\sigma\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            -alignment. ADS utilizes non-linear sampling by weighting the parameters of the degradation process for training uniformly degraded images, avoiding the long-tail problem.\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\sigma\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            -alignment controls the SD among positive samples; we identify a subset with small degraded distance, which aids contrastive learning in extracting representations more effectively. We extend AACL to several CNN-based and Transformer-based methods by coming up with a 6\u00a0\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            \u00a06 fair architecture with degradation representation fusion block (DRFB) and degradation representation fusion group (DRFG). DRFB and DRFG are designed for degradation representation fusion and image reconstruction, respectively. We evaluate on six types of degradation, and the improvement experiments on synthesized images show that our method balances performance and generalization and is applicable to networks with different architectures. The comparison experiments show that our improved methods achieve promising results compared to SOTA methods. Code is available at:\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/para999\/AACL\">https:\/\/github.com\/para999\/AACL<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3744650","type":"journal-article","created":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T12:05:33Z","timestamp":1749816333000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Alignment Contrastive Learning of Degradation Prediction for Blind Image Super-Resolution"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8520-6011","authenticated-orcid":false,"given":"Xianhong","family":"Wen","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3597-7124","authenticated-orcid":false,"given":"Sheng","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Computer and Electrical Engineering, Hunan University of Arts and Science, Changde, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2974-1166","authenticated-orcid":false,"given":"Bin","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1349-3399","authenticated-orcid":false,"given":"Xiangyuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Hunan Provincial Key Laboratory of Network Investigational Technology, Hunan Police Academy, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2900-3881","authenticated-orcid":false,"given":"Tianyu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering, and Mathematical Sciences, La Trobe University, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4143-6399","authenticated-orcid":false,"given":"Kehua","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China\u00a0and Furong Laboratory, Central South University, Changsha, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,12]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"126","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Agustsson Eirikur","year":"2017","unstructured":"Eirikur Agustsson and Radu Timofte. 2017. Ntire 2017 challenge on single image super-resolution: Dataset and study. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop., 126\u2013135."},{"key":"e_1_3_1_3_2","first-page":"1","volume-title":"Brit. Mach. Vis. Conf.","author":"Bevilacqua Marco","year":"2012","unstructured":"Marco Bevilacqua, Aline Roumy, Christine Guillemot, and Marie Line Alberi-Morel. 2012. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In Brit. Mach. Vis. Conf., 1\u201310."},{"key":"e_1_3_1_4_2","first-page":"3086","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Cai Jianrui","year":"2019","unstructured":"Jianrui Cai, Hui Zeng, Hongwei Yong, Zisheng Cao, and Lei Zhang. 2019. Toward real-world single image super-resolution: A new benchmark and a new model. In Proc. IEEE Int. Conf. Comput. Vis., 3086\u20133095."},{"key":"e_1_3_1_5_2","first-page":"1597","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In Proc. Int. Conf. Mach. Learn., 1597\u20131607."},{"issue":"1","key":"e_1_3_1_6_2","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1109\/TNNLS.2024.3362974","article-title":"Multicenter hierarchical federated learning with fault-tolerance mechanisms for resilient edge computing networks","volume":"36","author":"Chen Xiaohong","year":"2024","unstructured":"Xiaohong Chen, Guanying Xu, Xuesong Xu, Haichong Jiang, Zhiping Tian, and Tao Ma. 2024. Multicenter hierarchical federated learning with fault-tolerance mechanisms for resilient edge computing networks. IEEE Trans. Neural Netw. Learn. Syst. 36, 1 (2024), 47\u201361.","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"e_1_3_1_7_2","first-page":"12312","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Chen Zheng","year":"2023","unstructured":"Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong, Xiaokang Yang, and Fisher Yu. 2023. Dual aggregation transformer for image super-resolution. In Proc. IEEE Int. Conf. Comput. Vis., 12312\u201312321."},{"issue":"1","key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1109\/TMI.2024.3431192","article-title":"Unsupervised domain adaptation for EM image denoising with invertible networks","volume":"44","author":"Deng Shiyu","year":"2024","unstructured":"Shiyu Deng, Yinda Chen, Wei Huang, Ruobing Zhang, and Zhiwei Xiong. 2024. Unsupervised domain adaptation for EM image denoising with invertible networks. IEEE Trans. Med. Imaging 44, 1 (2024), 92\u2013105.","journal-title":"IEEE Trans. Med. Imaging"},{"key":"e_1_3_1_9_2","first-page":"576","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Dong Chao","year":"2015","unstructured":"Chao Dong, Yubin Deng, Chen Change Loy, and Xiaoou Tang. 2015. Compression artifacts reduction by a deep convolutional network. In Proc. IEEE Int. Conf. Comput. Vis., 576\u2013584."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_1_11_2","first-page":"16167","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Gou Yuanbiao","year":"2024","unstructured":"Yuanbiao Gou, Haiyu Zhao, Boyun Li, Xinyan Xiao, and Xi Peng. 2024. Test-time degradation adaptation for open-set image restoration. In Proc. Int. Conf. Mach. Learn., 16167\u201316177."},{"key":"e_1_3_1_12_2","first-page":"9199","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Gu Jinjin","year":"2021","unstructured":"Jinjin Gu and Chao Dong. 2021. Interpreting super-resolution networks with local attribution maps. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 9199\u20139208."},{"key":"e_1_3_1_13_2","first-page":"1604","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Gu Jinjin","year":"2019","unstructured":"Jinjin Gu, Hannan Lu, Wangmeng Zuo, and Chao Dong. 2019. Blind super-resolution with iterative kernel correction. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 1604\u20131613."},{"issue":"11","key":"e_1_3_1_14_2","first-page":"1","article-title":"ATMNet: Adaptive texture migration network for guided depth super-resolution","volume":"21","author":"Guo Kehua","year":"2024","unstructured":"Kehua Guo, Xuyang Tan, Xiangyuan Zhu, Shaojun Guo, and Zhipeng Xi. 2024. ATMNet: Adaptive texture migration network for guided depth super-resolution. ACM Trans. Multimedia Comput. Commun. Appl. 21, 11 (2024), 1\u201321.","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl"},{"key":"e_1_3_1_15_2","first-page":"1","article-title":"GAN prior-enhanced novel view synthesis from monocular degraded images","author":"Guo Kehua","year":"2025","unstructured":"Kehua Guo, Zheng Wu, Xianhong Wen, Shaojun Guo, Zhipeng Xi, and Tianyu Chen. 2025. GAN prior-enhanced novel view synthesis from monocular degraded images. IEEE Trans. Multimedia (2025), 1\u201311.","journal-title":"IEEE Trans. Multimedia"},{"key":"e_1_3_1_16_2","first-page":"1664","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Haris Muhammad","year":"2018","unstructured":"Muhammad Haris, Gregory Shakhnarovich, and Norimichi Ukita. 2018. Deep back-projection networks for super-resolution. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 1664\u20131673."},{"key":"e_1_3_1_17_2","first-page":"9729","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 9729\u20139738."},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3595924"},{"key":"e_1_3_1_20_2","first-page":"5197","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Huang Jia-Bin","year":"2015","unstructured":"Jia-Bin Huang, Abhishek Singh, and Narendra Ahuja. 2015. Single image super-resolution from transformed self-exemplars. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 5197\u20135206."},{"key":"e_1_3_1_21_2","unstructured":"Weiran Huang Mingyang Yi Xuyang Zhao and Zihao Jiang. 2021. Towards the generalization of contrastive self-supervised learning. arXiv:2111.00743. Retrieved from https:\/\/arxiv.org\/abs\/2111.00743"},{"key":"e_1_3_1_22_2","first-page":"5632","article-title":"Unfolding the alternating optimization for blind super resolution","volume":"33","author":"Luo Zhengxiong","year":"2020","unstructured":"Zhengxiong Luo, Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, and Tieniu Tan. 2020. Unfolding the alternating optimization for blind super resolution. Proc. Adv. Neural Inf. Process. Syst. 33 (2020), 5632\u20135643.","journal-title":"Proc. Adv. Neural Inf. Process. Syst"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3417333"},{"key":"e_1_3_1_24_2","first-page":"16236","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Jo Younghyun","year":"2021","unstructured":"Younghyun Jo, Seoung Wug Oh, Peter Vajda, and Seon Joo Kim. 2021. Tackling the ill-posedness of super-resolution through adaptive target generation. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 16236\u201316245."},{"key":"e_1_3_1_25_2","first-page":"694","volume-title":"Proc. Eur. Conf. Comput. Vis","author":"Johnson Justin","year":"2016","unstructured":"Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual losses for real-time style transfer and super-resolution. In Proc. Eur. Conf. Comput. Vis., 694\u2013711."},{"key":"e_1_3_1_26_2","first-page":"6065","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Khan Asif Hussain","year":"2024","unstructured":"Asif Hussain Khan, Christian Micheloni, and Niki Martinel. 2024. IDENet: Implicit degradation estimation network for efficient blind super resolution. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 6065\u20136075."},{"key":"e_1_3_1_27_2","first-page":"4681","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Ledig Christian","year":"2017","unstructured":"Christian Ledig, Lucas Theis, Ferenc Husz\u00e1r, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, et al. 2017. Photo-realistic single image super-resolution using a generative adversarial network. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 4681\u20134690."},{"key":"e_1_3_1_28_2","first-page":"517","volume-title":"In Proc. Eur. Conf. Comput. Vis","author":"Li Juncheng","year":"2018","unstructured":"Juncheng Li, Faming Fang, Kangfu Mei, and Guixu Zhang. 2018. Multi-scale residual network for image super-resolution. In Proc. Eur. Conf. Comput. Vis., 517\u2013532."},{"key":"e_1_3_1_29_2","first-page":"1833","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Liang Jingyun","year":"2021","unstructured":"Jingyun Liang, Jiezhang Cao, Guolei Sun, Kai Zhang, Luc Van Gool, and Radu Timofte. 2021. Swinir: Image restoration using swin transformer. In Proc. IEEE Int. Conf. Comput. Vis., 1833\u20131844."},{"key":"e_1_3_1_30_2","first-page":"574","volume-title":"In Proc. Eur. Conf. Comput. Vis","author":"Liang Jie","year":"2022","unstructured":"Jie Liang, Hui Zeng, and Lei Zhang. 2022. Efficient and degradation-adaptive network for real-world image super-resolution. In Proc. Eur. Conf. Comput. Vis., 574\u2013591."},{"key":"e_1_3_1_31_2","unstructured":"Kang Liao Zongsheng Yue Zhouxia Wang and Chen Change Loy. 2024. Denoising as adaptation: Noise-space domain adaptation for image restoration. arXiv:2406.18516. Retrieved from https:\/\/arxiv.org\/abs\/2406.18516"},{"key":"e_1_3_1_32_2","first-page":"136","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Lim Bee","year":"2017","unstructured":"Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, and Kyoung Mu Lee. 2017. Enhanced deep residual networks for single image super-resolution. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop., 136\u2013144."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3368923"},{"key":"e_1_3_1_34_2","first-page":"7455","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Liu Qingguo","year":"2024","unstructured":"Qingguo Liu, Chenyi Zhuang, Pan Gao, and Jie Qin. 2024. CDFormer: When degradation prediction embraces diffusion model for blind image super-resolution. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 7455\u20137464."},{"key":"e_1_3_1_35_2","first-page":"17642","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Luo Ziwei","year":"2022","unstructured":"Ziwei Luo, Haibin Huang, Lei Yu, Youwei Li, Haoqiang Fan, and Shuaicheng Liu. 2022. Deep constrained least squares for blind image super-resolution. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 17642\u201317652."},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01833-7"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126468"},{"key":"e_1_3_1_38_2","first-page":"416","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Martin David","year":"2001","unstructured":"David Martin, Charless Fowlkes, Doron Tal, and Jitendra Malik. 2001. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proc. IEEE Int. Conf. Comput. Vis., 416\u2013423."},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"e_1_3_1_40_2","first-page":"723","volume-title":"Proc. Eur. Conf. Comput. Vis","author":"Mou Chong","year":"2022","unstructured":"Chong Mou, Yanze Wu, Xintao Wang, Chao Dong, Jian Zhang, and Ying Shan. 2022. Metric learning based interactive modulation for real-world super-resolution. In Proc. Eur. Conf. Comput. Vis., 723\u2013740."},{"key":"e_1_3_1_41_2","unstructured":"Aaron van den Oord Yazhe Li and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv:1807.03748. Retrieved from https:\/\/arxiv.org\/abs\/1807.03748"},{"key":"e_1_3_1_42_2","first-page":"6075","volume-title":"IEEE Trans. Neural Netw. Learn. Syst","author":"Pan Zhuofu","year":"2023","unstructured":"Zhuofu Pan, Yalin Wang, Yue Cao, and Weihua Gui. 2023. VAE-based interpretable latent variable model for process monitoring. IEEE Trans. Neural Netw. Learn. Syst. 35, 5 (2023), 6075\u20136088."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102152"},{"key":"e_1_3_1_44_2","first-page":"24108","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Tian Yuchuan","year":"2024","unstructured":"Yuchuan Tian, Hanting Chen, Chao Xu, and Yunhe Wang. 2024. Image processing GNN: Breaking rigidity in super-resolution. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 24108\u201324117."},{"key":"e_1_3_1_45_2","first-page":"114","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Timofte Radu","year":"2017","unstructured":"Radu Timofte, Eirikur Agustsson, Luc Van Gool, Ming-Hsuan Yang, and Lei Zhang. 2017. Ntire 2017 challenge on single image super-resolution: Methods and results. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop., 114\u2013125."},{"key":"e_1_3_1_46_2","first-page":"4799","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Tong Tong","year":"2017","unstructured":"Tong Tong, Gen Li, Xiejie Liu, and Qinquan Gao. 2017. Image super-resolution using dense skip connections. In Proc. IEEE Int. Conf. Comput. Vis., 4799\u20134807."},{"key":"e_1_3_1_47_2","first-page":"11","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten Laurens","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 11 (2008).","journal-title":"J. Mach. Learn. Res"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02168-7"},{"key":"e_1_3_1_49_2","first-page":"10581","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Wang Longguang","year":"2021","unstructured":"Longguang Wang, Yingqian Wang, Xiaoyu Dong, Qingyu Xu, Jungang Yang, Wei An, and Yulan Guo. 2021. Unsupervised degradation representation learning for blind super-resolution. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 10581\u201310590."},{"key":"e_1_3_1_50_2","first-page":"1905","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Wang Xintao","year":"2021","unstructured":"Xintao Wang, Liangbin Xie, Chao Dong, and Ying Shan. 2021. Real-esrgan: Training real-world blind super-resolution with pure synthetic data. In Proc. IEEE Int. Conf. Comput. Vis., 1905\u20131914."},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3283922"},{"key":"e_1_3_1_52_2","first-page":"13095","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Xia Bin","year":"2023","unstructured":"Bin Xia, Yulun Zhang, Shiyin Wang, Yitong Wang, Xinglong Wu, Yapeng Tian, Wenming Yang, and Luc Van Gool. 2023. Diffir: Efficient diffusion model for image restoration. In Proc. IEEE Int. Conf. Comput. Vis., 13095\u201313105."},{"key":"e_1_3_1_53_2","unstructured":"Bin Xia Yulun Zhang Yitong Wang Yapeng Tian Wenming Yang Radu Timofte and Luc Van Gool. 2022. Knowledge distillation based degradation estimation for blind super-resolution. arXiv:2211.16928. Retrieved from https:\/\/arxiv.org\/abs\/2211.16928"},{"key":"e_1_3_1_54_2","first-page":"23153","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Yue Zongsheng","year":"2025","unstructured":"Zongsheng Yue, Kang Liao, and Chen Change Loy. 2025. Arbitrary-steps image super-resolution via diffusion inversion. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 23153\u201323163."},{"key":"e_1_3_1_55_2","first-page":"711","article-title":"On single image scale-up using sparse-representations","author":"Zeyde Roman","year":"2012","unstructured":"Roman Zeyde, Michael Elad, and Matan Protter. 2012. On single image scale-up using sparse-representations. In Int. Conf. Curv. Surf., 711\u2013730.","journal-title":"Int. Conf. Curv. Surf."},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3398685"},{"key":"e_1_3_1_57_2","first-page":"4791","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Zhang Kai","year":"2021","unstructured":"Kai Zhang, Jingyun Liang, Luc Van Gool, and Radu Timofte. 2021. Designing a practical degradation model for deep blind image super-resolution. In Proc. IEEE Int. Conf. Comput. Vis., 4791\u20134800."},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"e_1_3_1_59_2","first-page":"3262","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Zhang Kai","year":"2018","unstructured":"Kai Zhang, Wangmeng Zuo, and Lei Zhang. 2018. Learning a single convolutional super-resolution network for multiple degradations. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 3262\u20133271."},{"key":"e_1_3_1_60_2","first-page":"41078","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Zhang Ruofan","year":"2023","unstructured":"Ruofan Zhang, Jinjin Gu, Haoyu Chen, Chao Dong, Yulun Zhang, and Wenming Yang. 2023. Crafting training degradation distribution for the accuracy-generalization trade-off in real-world super-resolution. In Proc. Int. Conf. Mach. Learn., 41078\u201341091."},{"key":"e_1_3_1_61_2","first-page":"586","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Zhang Richard","year":"2018","unstructured":"Richard Zhang, Phillip Isola, Alexei A. Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 586\u2013595."},{"key":"e_1_3_1_62_2","first-page":"21003","article-title":"Real-world image super-resolution as multi-task learning","volume":"36","author":"Zhang Wenlong","year":"2024","unstructured":"Wenlong Zhang, Xiaohui Li, Guangyuan Shi, Xiangyu Chen, Yu Qiao, Xiaoyun Zhang, Xiao-Ming Wu, and Chao Dong. 2024. Real-world image super-resolution as multi-task learning. Proc. Adv. Neural Inf. Process. Syst. 36 (2024), 21003\u201321022.","journal-title":"Proc. Adv. Neural Inf. Process. Syst"},{"key":"e_1_3_1_63_2","first-page":"527","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Zhang Wenlong","year":"2022","unstructured":"Wenlong Zhang, Guangyuan Shi, Yihao Liu, Chao Dong, and Xiao-Ming Wu. 2022. A closer look at blind super-resolution: Degradation models, baselines, and performance upper bounds. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 527\u2013536."},{"key":"e_1_3_1_64_2","first-page":"286","volume-title":"In Proc. Eur. Conf. Comput. Vis","author":"Zhang Yulun","year":"2018","unstructured":"Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. 2018. Image super-resolution using very deep residual channel attention networks. In Proc. Eur. Conf. Comput. Vis., 286\u2013301."},{"key":"e_1_3_1_65_2","first-page":"2472","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit","author":"Zhang Yulun","year":"2018","unstructured":"Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu. 2018. Residual dense network for image super-resolution. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2472\u20132481."},{"issue":"2","key":"e_1_3_1_66_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3616495","article-title":"Contrastive attention-guided multi-level feature registration for reference-based super-resolution","volume":"20","author":"Zheng Jianwei","year":"2023","unstructured":"Jianwei Zheng, Yu Liu, Yuchao Feng, Honghui Xu, and Meiyu Zhang. 2023. Contrastive attention-guided multi-level feature registration for reference-based super-resolution. ACM Trans. Multimedia Comput. Commun. Appl. 20, 2 (2023), 1\u201321.","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3744650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T20:37:38Z","timestamp":1755031058000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3744650"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,12]]},"references-count":65,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8,31]]}},"alternative-id":["10.1145\/3744650"],"URL":"https:\/\/doi.org\/10.1145\/3744650","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,12]]},"assertion":[{"value":"2024-11-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}