{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T16:47:10Z","timestamp":1773852430408,"version":"3.50.1"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62401357, 62201339, 62371288, and 62320106003"],"award-info":[{"award-number":["62401357, 62201339, 62371288, and 62320106003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>Image denoising remains a challenging problem due to the ill-posed nature of recovering clean images from noisy observations. Prior-based modeling plays a vital role in addressing this challenge. Low-rank priors effectively exploit non-local self-similarity by modeling correlations across similar images, but often over-smooth fine textures. In contrast, sparse priors, especially in the form of Convolutional Sparse Coding (CSC), excel at preserving high-frequency texture details, yet typically neglect the structure across images. Recent unfolded CSC networks have improved denoising performance by combining CSC with deep networks, but most of them rely solely on sparsity, overlooking the complementary low-rank structure information. To overcome these limitations, we propose UCSC-LR, the first interpretable unfolded CSC network that jointly leverages both sparse and low-rank priors within a unified architecture. UCSC-LR unrolls both the Iterative Shrinkage-Thresholding Algorithm (ISTA) and Singular Value Thresholding (SVT) to strictly implement alternating minimization, enabling simultaneous pursuit of sparse representations and low-rank reconstructions. A dedicated Fusion Net is introduced to adaptively integrate features from the two priors, allowing the model to preserve both texture and structural content. To further enhance performance on color image denoising, UCSC-LR incorporates a lightweight channel attention mechanism to capture inter-channel dependencies. With shared, pre-learned convolutional dictionaries and efficient parameterization, UCSC-LR achieves state-of-the-art performance with low model complexity. Extensive experiments on grayscale, blind, and color denoising tasks validate the effectiveness of the proposed method, consistently surpassing existing CSC-based and deep learning-based denoisers.<\/jats:p>","DOI":"10.1145\/3788690","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T14:07:04Z","timestamp":1768831624000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Unfolding Convolutional Sparse Coding With Low-rank-Guided Hybrid Priors for Image Denoising"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2305-8067","authenticated-orcid":false,"given":"Yifan","family":"Zhao","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9923-8016","authenticated-orcid":false,"given":"Ziyang","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6608-5700","authenticated-orcid":false,"given":"Duoduo","family":"Xue","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7551-1137","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Aerospace Control Technology Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-5778","authenticated-orcid":false,"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2888-594X","authenticated-orcid":false,"given":"Chenglin","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9694-9880","authenticated-orcid":false,"given":"Junni","family":"Zou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4552-0029","authenticated-orcid":false,"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.5220\/0013157700003912"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1137\/080738970"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068646"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941319"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.901238"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3334624"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3348804"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110676"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2027565"},{"key":"e_1_3_1_12_2","unstructured":"Maryam Fazel. 2002. Matrix Rank Minimization with Applications. Ph.D. Dissertation. Stanford University."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00259"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3141251"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2018.2840334"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.366"},{"key":"e_1_3_1_17_2","first-page":"222","volume-title":"Proceedings of the 18th European Conference on Computer Vision","author":"Guo Hang","year":"2024","unstructured":"Hang Guo, Jinmin Li, Tao Dai, Zhihao Ouyang, Xudong Ren, and Shu-Tao Xia. 2024. MambaIR: A simple baseline for image restoration with state-space model. In Proceedings of the 18th European Conference on Computer Vision. Springer, 222\u2013241."},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00181"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.09.021"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2025.3539021"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2022.3172842"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01753"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_3_1_24_2","first-page":"1673","volume-title":"Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS \u201918)","author":"Liu Ding","year":"2018","unstructured":"Ding Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, and Thomas S. Huang. 2018. Non-local recurrent network for image restoration. In Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS \u201918). Curran Associates, Inc., 1673\u20131682."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1137\/17M1145689"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.39"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1137\/20M1313167"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ac65ac"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3451693"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3201708"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01688"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049961"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00849"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3090531"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454491"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183835"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462313"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.08.022"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3429345"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2023.3340612"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106755"},{"key":"e_1_3_1_42_2","first-page":"231","volume-title":"Proceedings of the 11th Asian Conference on Computer Vision","author":"Wang Shenlong","year":"2012","unstructured":"Shenlong Wang, Lei Zhang, and Yan Liang. 2012. Nonlocal spectral prior model for low-level vision. In Proceedings of the 11th Asian Conference on Computer Vision. Springer, 231\u2013244."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2025.109886"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110291"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.125"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3566125"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233589"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2023.109284"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_3"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3144630"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2958309"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2786469"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.145"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088914"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2839891"},{"key":"e_1_3_1_60_2","first-page":"1","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Zhang Yulun","year":"2019","unstructured":"Yulun Zhang, Kunpeng Li, Kai Li, Bineng Zhong, and Yun Fu. 2019. Residual non-local attention networks for image restoration. In Proceedings of the 7th International Conference on Learning Representations. OpenReview.net, 1\u201318."},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00069"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.339"},{"key":"e_1_3_1_63_2","unstructured":"James Townsend. 2016. Differentiating the Singular Value Decomposition. Technical Report. Retrieved from https:\/\/j-towns.github.io\/papers\/svd-derivative.pdf"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45054-8_36"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1137\/090771806"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2025.112817"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1137\/130938700"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T03:48:36Z","timestamp":1773546516000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788690"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,27]]},"references-count":66,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3788690"],"URL":"https:\/\/doi.org\/10.1145\/3788690","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,27]]},"assertion":[{"value":"2025-06-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}