Abstract
Image restoration has been an integral part of image processing research with the goal of converting degraded images into clear ones. While some networks have achieved state-of-the-art results through architecture and module design, little attention has been paid to the adaptation of normalization methods in image restoration tasks. Normalization methods are crucial in deep learning. In this work, we attempt to combine gating mechanisms with normalization methods. Gated mechanisms are popular in feature extraction and information filtering, and combining them with normalization methods has potential for designing image restoration algorithms. Firstly, we propose a Simple Gated Attention Unit (SGAU), a block using a simple gating mechanism to validate the potential of gating mechanisms. Then, we propose a new normalization block, Gated Instance Normalization (GIN), and introduce a new normalization method, Global Response Normalization (GRN), for image restoration tasks. Both GIN and GRN combine gating mechanisms with normalization methods for feature extraction, fusion, and integration. Finally, we propose a two-stage network, Gated Normalization Network (GNNet), utilizing GIN and GRN as blocks to effectively extract and filter information. Deep separable convolutions are used in the deep layers to reduce parameters while preserving spatial information, improving local feature perception. An improved cross-stage feature fusion (ICSFF) block is used for feature information transfer between stages, and a supervised attention module (SAM) is used as input to the second stage network from the first stage output. Through various image restoration tasks, we achieve 32.93 dB PSNR on GoPro, 30.42 dB PSNR on HIDE for image deblurring, 39.94 dB PSNR on SIDD for real-world denoising, and good performance in Gaussian white noise denoising and image deraining tasks. Moreover, the GIN and GRN only generated a small number of gated weight and bias parameters, and compared to other multi-stage networks, the model size is reduced, and computational complexity is well balanced.














Similar content being viewed by others
Data availability
The data presented in this study are available on request from the first author.
References
Ye J, Zhang Y (2019) MAP-based image denoising with structured sparsity and Gaussian scale mixture. Pattern Anal Appl 22:965–977. https://doi.org/10.1007/s10044-018-0692-5
Su Z, Wenbo W, Zhang W (2023) Regularized denoising latent subspace based linear regression for image classification. Pattern Anal Appl 2023:1–18. https://doi.org/10.1007/s10044-023-01149-9
Joseph Raj AN, Junmin C, Nersisson R et al (2022) Bilingual text detection from natural scene images using faster R-CNN and extended histogram of oriented gradients. Pattern Anal Appl 25(4):1001–1013. https://doi.org/10.1007/s10044-022-01066-3
Zhang K, Zuo W, Zhang L (2018) FFDNet: Toward a fast and flexible solution for CNN-based image denoising. IEEE Trans Image Process 27(9):4608–4622. https://doi.org/10.1109/TIP.2018.2839891
Zhang Y, Tian Y, Kong Y et al (2020) Residual dense network for image restoration. IEEE Trans Pattern Anal Mach Intell 43(7):2480–2495
Zamir SW, Arora A, Khan S et al (2021) Multi-stage progressive image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 14821–14831
Tsai FJ, Peng YT, Tsai CC et al (2022) Banet: a blur-aware attention network for dynamic scene deblurring. IEEE Trans Image Process 31:6789–6799. https://doi.org/10.1109/TIP.2022.3216216
Mei Y, Fan Y, Zhang Y et al (2023) Pyramid Attention Network for Image Restoration. Int J Comput Vision 2023:1–19. https://doi.org/10.1007/s11263-023-01843-5
Anwar S, Barnes N (2020) Densely residual laplacian super-resolution. IEEE Trans Pattern Anal Mach Intell 44(3):1192–1204. https://doi.org/10.1109/TPAMI.2020.3021088
Zhou J, Meng M, Xing J et al (2021) Iterative feature refinement with network-driven prior for image restoration. Pattern Anal Appl 24:1623–1634
Zhang K, Zuo W, Chen Y et al (2017) Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Trans Image Process 26(7):3142–3155
Khan S, Naseer M, Hayat M et al (2022) Transformers in vision: A survey. ACM Comput Surv (CSUR) 54(10s):1–41. https://doi.org/10.1145/3505244
Liu Z, Lin Y, Cao Y et al (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 10012–10022
Liang J, Cao J, Sun G et al (2021) Swinir: Image restoration using swin transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1833–1844
Zamir SW, Arora A, Khan S et al (2022) Restormer: Efficient transformer for high-resolution image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5728–5739
Wang Z, Cun X, Bao J et al (2022) Uformer: A general u-shaped transformer for image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 17683–17693
Xue T, Ma P (2023) TC-net: transformer combined with cnn for image denoising. Appl Intell 53(6):6753–6762. https://doi.org/10.1007/s10489-022-03785-w
Dauphin YN, Fan A, Auli M et al (2017) Language modeling with gated convolutional networks. In: International conference on machine learning, (PMLR), pp 933–941
Kupyn O, Martyniuk T, Wu J et al (2019) Deblurgan-v2: Deblurring (orders-of-magnitude) faster and better. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8878–8887
Pan J, Dong J, Liu Y et al (2020) Physics-based generative adversarial models for image restoration and beyond. IEEE Trans Pattern Anal Mach Intell 43(7):2449–2462. https://doi.org/10.1109/TPAMI.2020.2969348
Chen L, Lu X, Zhang J et al (2021) Hinet: Half instance normalization network for image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 182–192
Yue Z, Zhao Q, Zhang L et al (2020) Dual adversarial network: Toward real-world noise removal and noise generation. Computer Vision–ECCV 2020. Springer International Publishing, Cham, pp 41–58
Zhang K, Li Y, Zuo W et al (2021) Plug-and-play image restoration with deep denoiser prior. IEEE Trans Pattern Anal Mach Intell 44(10):6360–6376
Chen L, Chu X, Zhang X et al (2022) Simple baselines for image restoration. Computer Vision–ECCV 2022. Springer International Publishing, Cham, pp 17–33
Ko K, Koh YJ, Kim CS (2022) Blind and compact denoising network based on noise order learning. In: IEEE Trans Image Process, pp 1657–1670
Li J, Yang H, Yi Q et al (2022) Multiple degradation and reconstruction network for single image denoising via knowledge distillation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 558–567
Tian C, Zheng M, Zuo W et al (2024) A cross Transformer for image denoising. Inform Fusion 102:102043
Tu Z, Talebi H, Zhang H et al (2022) Maxim: Multi-axis mlp for image processing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5769–5780
Hua W, Dai Z, Liu H et al (2022) Transformer quality in linear time. In: International conference on machine learning, (PMLR), pp 9099–9117
Muthusamy D, Sathyamoorthy S (2023) Feature Sampling based on Multilayer Perceptive Neural Network for image quality assessment. Eng Appl Artif Intell 121:106015
Muthusamy D, Sathyamoorthy S (2022) Deep belief network for solving the image quality assessment in full reference and no reference model. Neural Comput Appl 34(24):21809–21833
Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1251–1258
Woo S, Debnath S, Hu R et al (2023) Convnext v2: Co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 16133–16142
Chu X, Chen L, Chen C et al (2022) Improving image restoration by revisiting global information aggregation. Computer Vision–ECCV 2022. Springer International Publishing, Cham, pp 53–71
Zhang H, Sindagi V, Patel VM (2019) Image de-raining using a conditional generative adversarial network. IEEE Trans Circuits Syst Video Technol 30(11):3943–3956. https://doi.org/10.1109/TCSVT.2019.2920407
Yang W, Tan RT, Feng J et al (2017) Deep joint rain detection and removal from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1357–1366
Fu X, Huang J, Zeng D et al (2017) Removing rain from single images via a deep detail network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3855–3863
Zhang H, Patel VM (2018) Density-aware single image de-raining using a multi-stream dense network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 695–704
Martin D, Fowlkes C, Tal D et al (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistic. In: Proceedings Eighth IEEE International Conference on Computer Vision. pp 416–423
Timofte R, Agustsson E, Van Gool L et al (2017) Ntire 2017 challenge on single image super-resolution: Methods and results. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops. pp 114–125
Agustsson E, Timofte R (2017) Ntire 2017 challenge on single image super-resolution: Dataset and study. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops. pp 126–135
Ma K, Duanmu Z, Wu Q et al (2016) Waterloo exploration database: New challenges for image quality assessment models. IEEE Trans Image Process 26(2):1004–1016
Roth S, Black MJ (2005) Fields of experts: A framework for learning image priors. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2: 860–867
Huang JB, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 5197–5206
Franzen R (1999) Kodak lossless true color image suite. source: http://r0k.us/graphics/kodak
Abdelhamed A, Lin S, Brown MS (2018) A high-quality denoising dataset for smartphone cameras. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1692–1700
Nah S, Hyun Kim T, Mu Lee K (2017) Deep multi-scale convolutional neural network for dynamic scene deblurring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3883–3891
Shen Z, Wang W, Lu X et al (2019) Human-aware motion deblurring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5572–5581
Fu X, Huang J, Ding X et al (2017) Clearing the skies: A deep network architecture for single-image rain removal. IEEE Trans Image Process 26(6):2944–2956. https://doi.org/10.1109/TIP.2017.2691802
Jiang K, Wang Z, Yi P et al (2020) Multi-scale progressive fusion network for single image deraining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8346–8355
Anwar S, Barnes N, Petersson L (2021) Attention-based real image restoration. IEEE Transactions on Neural Networks and Learning Systems
Cho SJ, Ji SW, Hong JP et al (2021) Rethinking coarse-to-fine approach in single image deblurring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4641–4650
Cheng S, Wang Y, Huang H et al (2021) Nbnet: Noise basis learning for image denoising with subspace projection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4896–4906
Gu S, Zhang L, Zuo W et al (2014) Weighted nuclear norm minimization with application to image Denoising. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2862–2869
Zhang K, Zuo W, Gu S et al (2017) Learning deep CNN denoiser prior for image Restoration. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3929–3938
Li L, Pan J, Lai WS et al (2020) Dynamic scene deblurring by depth guided model. IEEE Trans Image Process 29:5273–5288
Zhang K, Luo W, Zhong Y et al (2020) Deblurring by realistic blurring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2737–2746
Cai J, Zuo W, Zhang L (2020) Dark and bright channel prior embedded network for dynamic scene deblurring. IEEE Trans Image Process 29:6885–6897
Purohit K, Suin M, Rajagopalan AN et al (2021) Spatially-adaptive image restoration using distortion-guided networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2309–2319
Su J, Xu B, Yin H (2022) A survey of deep learning approaches to image restoration. Neurocomputing 487:46–65
Funding
This work was funded by the Natural Science Research of Jiangsu Higher Education Institutions of China (Grants No. 22KJD140004) and 2022 Qixia District Key R&D Project (Grants No. ZY202224).
Author information
Ethics declarations
Competing interests
The authors declare no competing interests.
Conflict of interest
We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Ethical approval
This declaration is not applicable.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, Q., Wang, H., Zang, L. et al. Gated normalization unit for image restoration. Pattern Anal Applic 28, 16 (2025). https://doi.org/10.1007/s10044-024-01393-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10044-024-01393-7