{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:10:24Z","timestamp":1765339824583,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"name":"Innovation Capability Support Program of Shaanxi","award":["2022TD-23"],"award-info":[{"award-number":["2022TD-23"]}]},{"name":"Natural Science Foundation of China","award":["62302369, 62472336, 61991451"],"award-info":[{"award-number":["62302369, 62472336, 61991451"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755057","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:56:43Z","timestamp":1761371803000},"page":"3370-3379","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Visual Quality: Fidelity-Oriented Diffusion Model for Real-world Image Super-Resolution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2358-9091","authenticated-orcid":false,"given":"Zhenxuan","family":"Fang","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8523-0842","authenticated-orcid":false,"given":"Shuaibo","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9632-985X","authenticated-orcid":false,"given":"Weisheng","family":"Dong","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9375-5426","authenticated-orcid":false,"given":"Junwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2358-0293","authenticated-orcid":false,"given":"Fangfang","family":"Wu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2067-2763","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"State University of New York at Albany, Albany, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2179-3292","authenticated-orcid":false,"given":"Guangming","family":"Shi","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2364116"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_12"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00318"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547833"},{"key":"e_1_3_2_1_7_1","volume-title":"Image quality assessment: Unifying structure and texture similarity","author":"Ding Keyan","year":"2020","unstructured":"Keyan Ding, Kede Ma, Shiqi Wang, and Eero P Simoncelli. 2020. Image quality assessment: Unifying structure and texture similarity. IEEE transactions on pattern analysis and machine intelligence 44, 5 (2020), 2567--2581."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings, Part IV 13","author":"Dong Chao","year":"2014","unstructured":"Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. 2014. Learning a deep convolutional network for image super-resolution. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part IV 13. Springer, 184--199."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings, Part II 14","author":"Dong Chao","year":"2016","unstructured":"Chao Dong, Chen Change Loy, and Xiaoou Tang. 2016. Accelerating the super-resolution convolutional neural network. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part II 14. Springer, 391--407."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2022.3233185"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01736"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00308"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00435"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2014.0140"},{"key":"e_1_3_2_1_15_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00764"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02052"},{"key":"e_1_3_2_1_18_1","volume-title":"Weight Uncertainty Network for Low-Light Image Enhancement. In International Conference on Intelligent Computing. Springer, 106--117","author":"Jin Yutao","year":"2024","unstructured":"Yutao Jin, Yue Sun, and Xiaoyan Chen. 2024. Weight Uncertainty Network for Low-Light Image Enhancement. In International Conference on Intelligent Computing. Springer, 106--117."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_21_1","volume-title":"What uncertainties do we need in Bayesian deep learning for computer vision? Advances in neural information processing systems 30","author":"Kendall Alex","year":"2017","unstructured":"Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in Bayesian deep learning for computer vision? Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_33"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"e_1_3_2_1_27_1","volume-title":"Diffbir: Towards blind image restoration with generative diffusion prior. arXiv preprint arXiv:2308.15070","author":"Lin Xinqi","year":"2023","unstructured":"Xinqi Lin, Jingwen He, Ziyan Chen, Zhaoyang Lyu, Bo Dai, Fanghua Yu, Wanli Ouyang, Yu Qiao, and Chao Dong. 2023. Diffbir: Towards blind image restoration with generative diffusion prior. arXiv preprint arXiv:2308.15070 (2023)."},{"key":"e_1_3_2_1_28_1","first-page":"16398","article-title":"Uncertainty-driven loss for single image super-resolution","volume":"34","author":"Ning Qian","year":"2021","unstructured":"Qian Ning, Weisheng Dong, Xin Li, Jinjian Wu, and Guangming Shi. 2021. Uncertainty-driven loss for single image super-resolution. Advances in Neural Information Processing Systems 34 (2021), 16398--16409.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115428"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.149"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_33_1","volume-title":"Kelvin CK Chan, and Chen Change Loy","author":"Wang Jianyi","year":"2024","unstructured":"Jianyi Wang, Zongsheng Yue, Shangchen Zhou, Kelvin CK Chan, and Chen Change Loy. 2024. Exploiting diffusion prior for real-world image super-resolution. International Journal of Computer Vision (2024), 1--21."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01044"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"e_1_3_2_1_36_1","volume-title":"U-MedSAM: Uncertainty-aware MedSAM for Medical Image Segmentation. arXiv preprint arXiv:2408.08881","author":"Wang Xin","year":"2024","unstructured":"Xin Wang, Xiaoyu Liu, Peng Huang, Pu Huang, Shu Hu, and Hongtu Zhu. 2024. U-MedSAM: Uncertainty-aware MedSAM for Medical Image Segmentation. arXiv preprint arXiv:2408.08881 (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00070"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the European conference on computer vision (ECCV) workshops. 0--0.","author":"Wang Xintao","year":"2018","unstructured":"Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. 2018. Esrgan: Enhanced super-resolution generative adversarial networks. In Proceedings of the European conference on computer vision (ECCV) workshops. 0--0."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings, Part VIII 16","author":"Wei Pengxu","year":"2020","unstructured":"Pengxu Wei, Ziwei Xie, Hannan Lu, Zongyuan Zhan, Qixiang Ye, Wangmeng Zuo, and Liang Lin. 2020. Component divide-and-conquer for real-world image super-resolution. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VIII 16. Springer, 101--117."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01318"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"e_1_3_2_1_43_1","volume-title":"Pixel-aware stable diffusion for realistic image super-resolution and personalized stylization. arXiv preprint arXiv:2308.14469","author":"Yang Tao","year":"2023","unstructured":"Tao Yang, Rongyuan Wu, Peiran Ren, Xuansong Xie, and Lei Zhang. 2023. Pixel-aware stable diffusion for realistic image super-resolution and personalized stylization. arXiv preprint arXiv:2308.14469 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_32"},{"key":"e_1_3_2_1_45_1","volume-title":"Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling. arXiv preprint arXiv:2410.11236","author":"Zhang Guiyu","year":"2024","unstructured":"Guiyu Zhang, Huan-ang Gao, Zijian Jiang, Hao Zhao, and Zhedong Zheng. 2024. Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling. arXiv preprint arXiv:2410.11236 (2024)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00475"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00319"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00262"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2189576"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:08:22Z","timestamp":1765339702000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755057"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3755057","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755057","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}