{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T10:14:32Z","timestamp":1784888072635,"version":"3.55.0"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62421004"],"award-info":[{"award-number":["62421004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Commission of Science and Technology, China","award":["23010500100"],"award-info":[{"award-number":["23010500100"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>\n                    Convolutional Neural Network (CNN) and Vision Transformer (ViT) have revolutionized the field of image super-resolution (SR). However, their complexity poses challenges for resource\u2014constrained scenarios, particularly due to the high computational demands of Transformers and their excessive reliance on global information. To tackle these challenges, we propose a Multi-Channel Feature Integration Network (MCFINet), designed to maximize input pixel utilization while minimizing computational overhead. It integrates both local and global features within the channels, thereby exploiting their complementary advantages. First, the designed Feature Integration Block (FIB) effectively captures local information and improves visual quality by enhancing the mapping of non-local features. Subsequently, we utilize the Adaptive Channel Fusion Block (ACFB), which strengthens the interaction between features and channels while maintaining computational efficiency. Finally, for SR task on resource-constrained surface scenarios, we propose a more suitable pre-training method, which further boosts the model\u2019s learning ability. Evaluation results indicate that the proposed MCFINet achieves a better balance between lightweight design and high-quality restoration on both standard evaluation datasets and water surface target datasets. Specifically, compared to the traditional SwinIR-L, MCFINet reduces model training time and runtime by 12% on the test set, while also decreasing model complexity by 43%. Our codes are available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Lcasjz\/MCFINet\">https:\/\/github.com\/Lcasjz\/MCFINet<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3777465","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T16:05:03Z","timestamp":1763568303000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["MCFINet: A Cost-Efficient Multi-Channel Feature Integration Network for Surface Scenarios Image Super-Resolution"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1117-0051","authenticated-orcid":false,"given":"Liangcheng","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9737-6765","authenticated-orcid":false,"given":"Yueying","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5921-5774","authenticated-orcid":false,"given":"Yuhao","family":"Qing","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1300-1769","authenticated-orcid":false,"given":"Dan","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6727-6190","authenticated-orcid":false,"given":"Li","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering North China University of Water Resources and Electric Power, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"issue":"8","key":"e_1_3_2_3_2","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1109\/TUFFC.2024.3411711","article-title":"Super resolution ultrasound imaging using the erythrocytes\u2014Part I: Density images","volume":"71","author":"Jensen J. A.","year":"2024","unstructured":"J. A. Jensen, M. A. Naji, S. K. Pr\u00e6sius, I. Taghavi, M. Schou, and L. N. Hansen. 2024. Super resolution ultrasound imaging using the erythrocytes\u2014Part I: Density images. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control 71, 8 (2024), 925\u2013944.","journal-title":"IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3547042"},{"key":"e_1_3_2_5_2","first-page":"1","volume-title":"Proceedings of the 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ)","author":"Fatima F. N.","year":"2020","unstructured":"F. N. Fatima. 2020. AI in photography: Scrutinizing implementation of super-resolution techniques in photo-editors. In Proceedings of the 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ). IEEE, 1\u20136."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.007"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"e_1_3_2_10_2","first-page":"252","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Ahn N.","year":"2018","unstructured":"N. Ahn, B. Kang, and K. A. Sohn. 2018. Fast, accurate, and lightweight super-resolution with cascading residual network. In Proceedings of the European Conference on Computer Vision, 252\u2013268."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00099"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01213"},{"key":"e_1_3_2_13_2","first-page":"359","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Zheng M.","year":"2024","unstructured":"M. Zheng, L. Sun, J. Dong, and J. Pan. 2024. SMFANet: A lightweight self-modulation feature aggregation network for efficient image super-resolution. In Proceedings of the European Conference on Computer Vision. Springer Nature, Cham, Switzerland, 359\u2013375."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301225"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3283856"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01183"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_18_2","unstructured":"X. Chen X. Wang W. Zhang X. Kong Y. Qiao J. Zhou and C. Dong. 2023. HAT: Hybrid attention transformer for image restoration. arXiv:2309.05239. Retrieved from https:\/\/arxiv.org\/abs\/2309.05239"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00206"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3546076"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3542966"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"M. Bevilacqua A. Roumy C. Guillemot and M. L. Alberi-Morel. 2012. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In Proceedings of the 23rd British Machine Vision Conference.","DOI":"10.5244\/C.26.135"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","first-page":"5559","DOI":"10.1109\/TNNLS.2024.3378420","article-title":"Real-world light field image super-resolution via degradation modulation","volume":"36","author":"Wang Y.","year":"2024","unstructured":"Y. Wang, Z. Liang, L. Wang, J. Yang, W. An, and Y. Guo. 2024. Real-world light field image super-resolution via degradation modulation. IEEE Transactions on Neural Networks and Learning Systems 36 (2024), 5559\u20135573.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3414838"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351084"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712594"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123253"},{"key":"e_1_3_2_33_2","first-page":"1","article-title":"A multilevel multimodal fusion transformer for remote sensing semantic segmentation","volume":"62","author":"Ma X.","year":"2024","unstructured":"X. Ma, X. Zhang, M. O. Pun, and M. Liu. 2024. A multilevel multimodal fusion transformer for remote sensing semantic segmentation. IEEE Transactions on Geoscience and Remote Sensing 62 (2024), 1\u201315.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","first-page":"1024","DOI":"10.1109\/TAI.2024.3508667","article-title":"Unformer: A transformer-based approach for adaptive multi-scale feature aggregation in underwater image enhancement","volume":"6","author":"Qing Y.","year":"2024","unstructured":"Y. Qing, Y. Wang, H. Yan, X. Xie, and Z. Wu. 2024. Unformer: A transformer-based approach for adaptive multi-scale feature aggregation in underwater image enhancement. IEEE Transactions on Artificial Intelligence 6 (2024), 1024\u20131037.","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1109\/JOE.2024.3525150","article-title":"HG2Former: HSV-gamma guided transformers for efficient underwater image enhancement","volume":"50","author":"Qing Y.","year":"2025","unstructured":"Y. Qing, L. Shen, Z. Fang, and Y. Wang. 2025. HG2Former: HSV-gamma guided transformers for efficient underwater image enhancement. IEEE Journal of Oceanic Engineering 50 (2025), 866\u2013878.","journal-title":"IEEE Journal of Oceanic Engineering"},{"key":"e_1_3_2_36_2","unstructured":"Y. Zhou Z. Li C. L. Guo L. Liu M. M. Cheng and Q. Hou. 2023. SRFormerV2: Taking a closer look at permuted self-attention for image super-resolution. arXiv:2303.09735. Retrieved from https:\/\/arxiv.org\/abs\/2303.09735"},{"key":"e_1_3_2_37_2","first-page":"6257","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chu S. C.","year":"2024","unstructured":"S. C. Chu, Z. C. Dou, J. S. Pan, S. Weng, and J. Li. 2024. HMANet: Hybrid multi-axis aggregation network for image super-resolution. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6257\u20136266."},{"key":"e_1_3_2_38_2","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/978-3-031-78305-0_19","volume-title":"Proceedings of the International Conference on Pattern Recognition","author":"Pramanick A.","year":"2025","unstructured":"A. Pramanick, U. Bheda, and A. Sur. 2025. ML-CrAIST: Multi-scale low-high frequency information-based cross attention with image super-resolving transformer. In Proceedings of the International Conference on Pattern Recognition. Springer, Cham, 291\u2013307."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16088-0"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.5555\/176313.176316"},{"key":"e_1_3_2_41_2","first-page":"6133","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hsu C. C.","year":"2024","unstructured":"C. C. Hsu, C. M. Lee, and Y. S. Chou. 2024. DRCT: Saving image super-resolution away from information bottleneck. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6133\u20136142."},{"key":"e_1_3_2_42_2","unstructured":"T. Dao and A. Gu. 2024. Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality. arXiv:2405.21060. Retrieved from https:\/\/arxiv.org\/abs\/2405.21060"},{"key":"e_1_3_2_43_2","unstructured":"A. Gu and T. Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv:2312.00752. Retrieved from https:\/\/arxiv.org\/abs\/2312.00752"},{"key":"e_1_3_2_44_2","first-page":"12021","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen J.","year":"2023","unstructured":"J. Chen, S. H. Kao, H. He, W. Zhuo, S. Wen, C. H. Lee, and S. H. G. Chan. 2023. Run, don\u2019t walk: Chasing higher FLOPS for faster neural networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12021\u201312031."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_46_2","unstructured":"W. Li X. Lu S. Qian J. Lu X. Zhang and J. Jia. 2021. On efficient transformer-based image pre-training for low-level vision. arXiv:2112.10175. Retrieved from https:\/\/arxiv.org\/abs\/2112.10175"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27413-8_47"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2020.2987895"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00262"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3374576"},{"key":"e_1_3_2_54_2","first-page":"20343","volume-title":"Advances in Neural Information Processing Systems","author":"Li W.","year":"2020","unstructured":"W. Li, K. Zhou, L. Qi, N. Jiang, J. Lu, and J. Jia. 2020. LAPAR: Linearly-assembled pixel-adaptive regression network for single image super-resolution and beyond. In Advances in Neural Information Processing Systems, Vol. 33, 20343\u201320355."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00488"},{"key":"e_1_3_2_56_2","first-page":"17314","volume-title":"Advances in Neural Information Processing Systems","author":"Sun L.","year":"2022","unstructured":"L. Sun, J. Pan, and J. Tang. 2022. ShuffleMixer: An efficient ConvNet for image super-resolution. In Advances in Neural Information Processing Systems, Vol. 35, 17314\u201317326."},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00908"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3777465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:20:50Z","timestamp":1768314050000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3777465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,13]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3777465"],"URL":"https:\/\/doi.org\/10.1145\/3777465","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,13]]},"assertion":[{"value":"2025-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}