{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:54:41Z","timestamp":1776696881843,"version":"3.51.2"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"name":"National Science and Technology Council, Taiwan","award":["NSTC114-2410-H-194-075-MY2"],"award-info":[{"award-number":["NSTC114-2410-H-194-075-MY2"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>Blind super-resolution (SR) aims to reconstruct high-resolution images from low-quality inputs under unknown degradation conditions. While numerous blind SR methods have been proposed in recent years, they still face critical limitations. Most approaches perform well under specific degradation patterns but struggle with complex scenarios involving multiple degradation factors and varying noise levels. This often leads to loss of structural integrity and fine details, resulting in suboptimal restoration quality. Furthermore, existing methods typically rely on convolutional neural networks (CNNs) with limited receptive fields, which hinders effective cross-domain information integration. Their inability to capture long-range dependencies compromises the reconstruction of global structures. In edge detection, conventional techniques frequently produce inaccurate or false edges, further degrading the quality of cross-domain integration and image restoration. To address these challenges, we propose Structural Integrity and Texture Fidelity Transformer (SITFFormer), a novel transformer-based framework for blind single-image SR. Our approach incorporates the Canny edge detection algorithm to accurately preserve true edges and suppress noise-induced artifacts, enhancing edge localization in complex and noisy environments. We also introduce the Cross-Domain Structure-Texture-Aware Network (CDSTNet), designed to integrate intra-domain and cross-domain features for comprehensive structure preservation and texture recovery. CDSTNet comprises two key modules: Cross-Domain Integration (CDI) that fuses intra- and cross-domain features to retain structural and textural details. Cross-Domain Learnable Attention (CDLA) that explores global dependencies, adaptively refines feature similarity, and filters out redundant non-local information. Both modules are equipped with a Cross-Attention Mechanism (CAM) to facilitate effective interaction and complementarity between domains, enhancing reconstruction fidelity. Extensive experiments on synthetic, noisy, and real-world datasets demonstrate that SITFFormer surpasses state-of-the-art methods in quantitative performance and visual quality, particularly in preserving structural integrity and recovering fine textures.<\/jats:p>","DOI":"10.1145\/3799233","type":"journal-article","created":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:46:39Z","timestamp":1773481599000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SITFFormer: A Blind Super-Resolution Framework Preserving Structural Integrity and Texture Fidelity"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4599-0744","authenticated-orcid":false,"given":"Wei-Yen","family":"Hsu","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, National Yang Ming Chiao Tung University, Tainan, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9236-4467","authenticated-orcid":false,"given":"Hsin-Yun","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Information Management, National Chung Cheng University, Chiayi, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5568-7562","authenticated-orcid":false,"given":"Chung-Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Information Management, National Chung Cheng University, Chiayi, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3735559"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3688802"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3639407"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592613"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3044209"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"e_1_3_1_10_2","first-page":"372","volume-title":"Computer Vision (ECCV \u201914)","author":"Yang Chih-Yuan","year":"2014","unstructured":"Chih-Yuan Yang, Chao Ma, and Ming-Hsuan Yang. 2014. Single-image super-resolution: A benchmark. In Computer Vision (ECCV \u201914). Springer International Publishing, 372\u2013386."},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094753"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01712"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.618"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00329"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454313"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00170"},{"key":"e_1_3_1_19_2","unstructured":"Zhengxiong Luo Yan Huang Shang Li Liang Wang and T. Tan. 2021. End-to-end alternating optimization for blind super resolution. Retrieved October 10 2024 from https:\/\/www.semanticscholar.org\/paper\/End-to-end-Alternating-Optimization-for-Blind-Super-Luo-Huang\/a54a68e55628d6d08848dd9b2ba15554bba8fb1b"},{"key":"e_1_3_1_20_2","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141. Ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, Curran Associates, Inc. Retrieved October 10, 2024 from https:\/\/papers.nips.cc\/paper_files\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3589209"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3735649"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3307666"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3229689"},{"key":"e_1_3_1_25_2","first-page":"5632","volume-title":"34th International Conference on Neural Information Processing Systems (NIPS \u201920)","author":"Luo Zhengxiong","year":"2020","unstructured":"Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, and Tieniu Tan. 2020. Unfolding the alternating optimization for blind super resolution. In 34th International Conference on Neural Information Processing Systems (NIPS \u201920). Curran Associates Inc., 5632\u20135643."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01597"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.135"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27413-8_47"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4020-z"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_16"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2753804"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01047"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00179"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00150"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00344"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3039574"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3579726"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3289958"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3152090"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3283922"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3359447"},{"key":"e_1_3_1_48_2","first-page":"384","volume-title":"2024 9th International Conference on Image, Vision and Computing (ICIVC)","author":"Sun Haochen","year":"2024","unstructured":"Haochen Sun, Yan Yuan, Lijuan Su, and Haotian Shao. 2024. Learning correction errors via frequency-self attention for blind image super-resolution. In 2024 9th International Conference on Image, Vision and Computing (ICIVC). IEEE, 384\u2013392."},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-60157-9"},{"key":"e_1_3_1_50_2","unstructured":"Feng Li Yixuan Wu Zichao Liang Runmin Cong Huihui Bai Yao Zhao and Meng Wang. 2024. BlindDiff: Empowering degradation modelling in diffusion models for blind image super-resolution. arXiv:2403.10211. Retrieved from https:\/\/arxiv.org\/abs\/2403.10211"},{"key":"e_1_3_1_51_2","unstructured":"Shao-Hao Lu Ren Wang Ching-Chun Huang and Wei-Chen Chiu. 2025. Boosting diffusion guidance via learning degradation-aware models for blind super resolution. arXiv:2501.08819. Retrieved from https:\/\/arxiv.org\/abs\/2501.08819"},{"key":"e_1_3_1_52_2","doi-asserted-by":"crossref","first-page":"105041","DOI":"10.1016\/j.dsp.2025.105041","article-title":"ParNet: Joint image super-resolution and blind denoising with expanded residual blocks and multi-scale ghost-gated metaformers","author":"Farhangfar Saghar","year":"2025","unstructured":"Saghar Farhangfar, Aryaz Baradarani, Mohammad Asadpour, Mohammad Ali Balafar, and Roman Gr Maev. 2025. ParNet: Joint image super-resolution and blind denoising with expanded residual blocks and multi-scale ghost-gated metaformers. Digital Signal Processing 160 (2025), 105041.","journal-title":"Digital Signal Processing"},{"key":"e_1_3_1_53_2","volume-title":"IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Zhang Mingjin","year":"2023","unstructured":"Mingjin Zhang, Chi Zhang, Qiming Zhang, Jie Guo, Xinbo Gao, and Jing Zhang. 2023. ESSAformer: Efficient transformer for hyperspectral image super-resolution. In IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"issue":"1","key":"e_1_3_1_54_2","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/TCYB.2022.3163294","article-title":"Fluid micelle network for image super-resolution reconstruction","volume":"53","author":"Zhang M.","year":"2023","unstructured":"M. Zhang, Q. Wu, J. Zhang, X. Gao, J. Guo, and D. Tao. 2023. Fluid micelle network for image super-resolution reconstruction. IEEE Transactions on Cybernetics 53, 1 (Jan. 2023), 578\u2013591.","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"2","key":"e_1_3_1_55_2","doi-asserted-by":"crossref","first-page":"1810","DOI":"10.1109\/TNNLS.2022.3185529","article-title":"Heat transfer-inspired network for image super-resolution reconstruction","volume":"35","author":"Zhang M.","year":"2024","unstructured":"M. Zhang, Q. Wu, J. Guo, Y. Li, and X. Gao. 2024. Heat transfer-inspired network for image super-resolution reconstruction. IEEE Transactions on Neural Networks and Learning Systems 35, 2 (Feb. 2024), 1810\u20131820.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_1_56_2","first-page":"6065\u2212","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6065\u22126075."},{"key":"e_1_3_1_57_2","doi-asserted-by":"crossref","first-page":"4556","DOI":"10.1109\/TIP.2024.3442613","article-title":"2024. Lightweight prompt learning implicit degradation estimation network for blind super resolution","author":"Khan Asif Hussain","year":"2024","unstructured":"Asif Hussain Khan, Christian Micheloni, and Niki Martinel. 2024. Lightweight prompt learning implicit degradation estimation network for blind super resolution. IEEE Transactions on Image Processing 33 (2024), 4556\u20134567.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_1_58_2","first-page":"832","volume-title":"Computer Vision and Pattern Recognition Conference","author":"Mehta Nancy","year":"2025","unstructured":"Nancy Mehta, Akshay Dudhane, Subrahmanyam Murala, and Radu Timofte. 2025. KernFusNet: Implicit kernel modulation and fusion for blind super-resolution. In Computer Vision and Pattern Recognition Conference, 832\u2013842."},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3462490"},{"key":"e_1_3_1_61_2","first-page":"1","article-title":"CDBGrad-BlindSR: Collaborative dual-branch network via gradient guidance for efficient blind super resolution","volume":"74","author":"Yang H.","year":"2025","unstructured":"H. Yang, S. Fu, K. Liu, and X. Yang. 2025. CDBGrad-BlindSR: Collaborative dual-branch network via gradient guidance for efficient blind super resolution. IEEE Transactions on Instrumentation and Measurement 74 (2025), 1\u201315.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_3_1_62_2","first-page":"13049","volume-title":"IEEE\/CVF International Conference on Computer Vision","author":"Xia Bin","year":"2023","unstructured":"Bin Xia, Yulun Zhang, Shiyin Wang, Yitong Wang, Xinglong Wu, and Yapeng Tian. 2023. DiffiR: Efficient diffusion model for image restoration. In IEEE\/CVF International Conference on Computer Vision, 13049\u201313059."},{"key":"e_1_3_1_63_2","volume-title":"British Machine Vision Conference","volume":"1","author":"Zhang X.","year":"2018","unstructured":"X. Zhang, H. Dong, Z. Hu, W.-S. Lai, F. Wang, and M.-H. Yang. 2018. Gated fusion network for joint image deblurring and super-resolution. In British Machine Vision Conference, 1\u201313. [Online]. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:51875491"},{"key":"e_1_3_1_64_2","first-page":"4096","volume-title":"IEEE\/CVF International Conference on Computer Vision","author":"Liang J.","year":"2021","unstructured":"J. Liang, G. Sun, K. Zhang, L. V. Gool, and R. Timofte. 2021. Mutual affine network for spatially variant kernel estimation in blind image superresolution. In IEEE\/CVF International Conference on Computer Vision, 4096\u20134105."},{"key":"e_1_3_1_65_2","first-page":"223","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Bai H.","year":"2021","unstructured":"H. Bai, S. Cheng, J. Tang, and J. Pan. 2021. Learning a cascaded non-local residual network for super-resolving blurry images. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 223\u2013232."},{"key":"e_1_3_1_66_2","first-page":"63","volume-title":"European Conference on Computer Vision Workshops","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 European Conference on Computer Vision Workshops, 63\u201379."},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3096327"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:10:25Z","timestamp":1776694225000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799233"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":66,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3799233"],"URL":"https:\/\/doi.org\/10.1145\/3799233","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2025-03-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}