{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T09:21:13Z","timestamp":1771579273066,"version":"3.50.1"},"reference-count":44,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T00:00:00Z","timestamp":1771545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shenyang Science and Technology Project","award":["23-503-6-18"],"award-info":[{"award-number":["23-503-6-18"]}]},{"name":"Fundamental Research Funds for the Universities of Liaoning Province","award":["LJ232410143060"],"award-info":[{"award-number":["LJ232410143060"]}]},{"name":"Scientific Research Platform Construction Project of the Education Department of Liaoning Province","award":["LJ232510143007"],"award-info":[{"award-number":["LJ232510143007"]}]},{"name":"Liaoning Provincial Applied Basic Research Project","award":["2025JH2\/101330120"],"award-info":[{"award-number":["2025JH2\/101330120"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>In recent years, Transformer architectures have excelled at modeling non-local information. This makes them suitable for image deraining. However, existing methods use dense self-attention. They compute all similarities between query and key tokens. This is inefficient. In practice, this approach can lead to the neglect of the most relevant information and result in a blurring effect of irrelevant representations during the feature aggregation process. To address this issue, this paper proposes an image deraining Transformer based on sparse non-local self-attention. The core of the network consists of multiple non-local feature extraction modules, primarily comprising a sparse self-attention network and a sparse feedforward network along the channel dimension. Specifically, we implement sparse attention by selecting the most useful similarities based on Top-k approximations. Furthermore, we have developed a sparse feedforward network to achieve more accurate representations for high-quality preservation results. Extensive experiments on benchmark datasets have demonstrated the effectiveness of our proposed method.<\/jats:p>","DOI":"10.3390\/computers15020133","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T08:50:03Z","timestamp":1771577403000},"page":"133","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Image Deraining Using Transformer Network with Sparse Non-Local Self-Attention"],"prefix":"10.3390","volume":"15","author":[{"given":"Xueying","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Electronic Information Engineering, Shenyang Aerospace University, Shenyang 110136, China"}]},{"given":"Yufeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic Information Engineering, Shenyang Aerospace University, Shenyang 110136, China"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1742","DOI":"10.1109\/TIP.2011.2179057","article-title":"Automatic single-image-based rain streaks removal via image decomposition","volume":"21","author":"Kang","year":"2011","journal-title":"IEEE Trans. Image Process."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Li, Y., Tan, R.T., Guo, X., Lu, J., and Brown, M.S. (2016). Rain streak removal using layer priors. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2016.299"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yu, Y., Yang, W., Tan, Y.P., and Kot, A.C. (2022). Towards robust rain removal against adversarial attacks: A comprehensive benchmark analysis and beyond. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.00592"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Fan, Z., Wu, X., Chen, X., and Li, Y. (2023). Learning to see in nighttime driving scenes with interfrequency priors. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE.","DOI":"10.1109\/CVPRW59228.2023.00444"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chen, X., Pan, J., and Dong, J. (2024). Bidirectional multi-scale implicit neural representations for image deraining. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.02421"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chai, G., Yang, R., Ge, J., and Chen, Y. (2025). A Hybrid Content-Aware Network for Single Image Deraining. Computers, 14.","DOI":"10.3390\/computers14070262"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1046","DOI":"10.1609\/aaai.v38i2.27865","article-title":"Rethinking multi-scale representations in deep deraining transformer","volume":"Volume 38","author":"Chen","year":"2024","journal-title":"Proceedings of the 38th AAAI Conference on Artificial Intelligence"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.cogr.2024.12.002","article-title":"DECTNet: A detail enhanced CNN-Transformer network for single-image deraining","volume":"5","author":"Wang","year":"2025","journal-title":"Cogn. Robot."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Chen, X., Pan, J., Jiang, K., Li, Y., Huang, Y., Kong, C., Dai, L., and Fan, Z. (2022). Unpaired deep image deraining using dual contrastive learning. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.00206"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"12892","DOI":"10.1609\/aaai.v38i11.29186","article-title":"FMRNet: Image deraining via frequency mutual revision","volume":"Volume 38","author":"Jiang","year":"2024","journal-title":"Proceedings of the 38th AAAI Conference on Artificial Intelligence"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2198","DOI":"10.1109\/LSP.2022.3212641","article-title":"Tao-net: Task-adaptive operation network for image restoration and enhancement","volume":"29","author":"Li","year":"2022","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Xu, N., and Yang, J.J. (2025). Leveraging Scene Geometry and Depth Information for Robust Image Deraining. Computers, 14.","DOI":"10.3390\/computers14010011"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zou, W., Wang, Y., Fu, X., and Cao, Y. (2022, January 18\u201324). Dreaming to prune image deraining networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00593"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yao, Y., Shi, Z., Hu, H., Li, J., Wang, G., and Liu, L. (2023). GSDerainNet: A deep network architecture based on a Gaussian shannon filter for single image deraining. Remote Sens., 15.","DOI":"10.3390\/rs15194825"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., and Yang, M.H. (2022). Restormer: Efficient transformer for high-resolution image restoration. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhou, H., Chen, H., Wu, X., and Li, Y. (2024). Dual-path multi-scale transformer for high-quality image deraining. 2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP), IEEE.","DOI":"10.1109\/MMSP61759.2024.10743477"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"104847","DOI":"10.1016\/j.dsp.2024.104847","article-title":"Multi-scale transformer with conditioned prompt for image deraining","volume":"156","author":"Wu","year":"2025","journal-title":"Digit. Signal Process."},{"key":"ref_18","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jia, J., and Koltun, V. (2020). Exploring self-attention for image recognition. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Gautam, A., Pawar, A., Joshi, A., Tazi, S.N., Chaudhary, S., Hambarde, P., Dudhane, A., Vipparthi, S., and Murala, S. (2025). Pureformer: Transformer-Based Image Denoising. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPRW67362.2025.00133"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"112374","DOI":"10.1016\/j.patcog.2025.112374","article-title":"Cross-domain-aware deep unfolding transformer for hyperspectral image super-resolution","volume":"172","author":"Cao","year":"2025","journal-title":"Pattern Recognit."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"8942","DOI":"10.1609\/aaai.v39i9.32967","article-title":"Motion-adaptive Transformer for Event-based Image Deblurring","volume":"Volume 39","author":"Xu","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"112448","DOI":"10.1016\/j.knosys.2024.112448","article-title":"Global sparse attention network for remote sensing image super-resolution","volume":"304","author":"Hu","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"21493","DOI":"10.1007\/s00521-025-11471-4","article-title":"Blind image super-resolution using swin transformer with unsupervised degradation and sparse attention","volume":"37","author":"Gendy","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_25","unstructured":"Yu, F., and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., and Cottrell, G. (2018). Understanding convolution for semantic segmentation. 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE.","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2944","DOI":"10.1109\/TIP.2017.2691802","article-title":"Clearing the skies: A deep network architecture for single-image rain removal","volume":"26","author":"Fu","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wei, W., Meng, D., Zhao, Q., Xu, Z., and Wu, Y. (2019). Semi-supervised transfer learning for image rain removal. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2019.00400"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Patel, V.M. (2018). Density-aware single image de-raining using a multi-stream dense network. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00079"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yasarla, R., and Patel, V.M. (2019). Uncertainty guided multi-scale residual learning-using a cycle spinning CNN for single image de-raining. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2019.00860"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, J., Lin, Z., Liu, H., and Zha, H. (2018). Recurrent squeeze-and-excitation context aggregation net for single image deraining. European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-030-01234-2_16"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ren, D., Zuo, W., Hu, Q., Zhu, P., and Meng, D. (2019). Progressive image deraining networks: A better and simpler baseline. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.00406"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kui Jiang, K., Wang, Z., Yi, P., Chen, C., Huang, B., Luo, Y., Ma, J., and Jiang, J. (2020). Multi-scale progressive fusion network for single image deraining. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.00837"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H., and Shao, L. (2021). Multi-stage progressive image restoration. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, Q., and Zhang, J. (2022). Deep generalized unfolding networks for image restoration. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.01688"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Lee, H., Choi, H., Sohn, K., and Min, D. (2022). KNN local attention for image restoration. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.00218"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., and Li, H. (2022). Uformer: A general u-haped transformer for image restoration. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"12978","DOI":"10.1109\/TPAMI.2022.3183612","article-title":"Image de-raining transformer","volume":"45","author":"Xiao","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Gao, N., Jiang, X., Zhang, X., and Deng, Y. (2024). Efficient frequency-domain image deraining with contrastive regularization. European Conference on Computer Vision, Springer Nature.","DOI":"10.1007\/978-3-031-72940-9_14"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Dong, G., Zheng, T., Cao, Y., Qing, L., and Ren, C. (2025). Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52734.2025.00700"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"3943","DOI":"10.1109\/TCSVT.2019.2920407","article-title":"Image de-raining using a conditional generative adversarial network","volume":"30","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yang, W., Tan, R.T., Feng, J., Liu, J., Guo, Z., and Yan, S. (2017). Deep joint rain detection and removal from a single image. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2017.183"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Fu, X., Huang, J., Zeng, D., Huang, Y., Ding, X., and Paisley, J. (2017). Removing rain from single images via a deep detail network. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2017.186"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/2\/133\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T08:55:04Z","timestamp":1771577704000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/2\/133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,20]]},"references-count":44,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["computers15020133"],"URL":"https:\/\/doi.org\/10.3390\/computers15020133","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,20]]}}}