Abstract
Deep convolutional neural networks (DCNN) have been widely used in the field of image denoising because of their fast inference and good performance. However, the design of networks for the DCNN is mostly empirical, and the interpretation and robustness of them remains a major challenge. Inspired by the total generalized variation method, this paper proposes a novel adaptive denoising network. It mainly improves the TGV algorithm in terms of two points. Firstly, the first and second order derivation term are replaced by the learnable operators. Secondly, the regularization terms are learned from the training data by using convolution networks other than the fixed ones. The network design derived from the process for tackling the denoising problem based on the primal-dual hybrid gradient optimization algorithm, is called TGVLNet- Total Generalized Variational-Liked Network, which allows for the image prior and the linear operators to be tuned differently in each iteration, and enhances the flexibility and generalization ability of the network. The experiment results of Gaussian noise removal and signal dependent noise removal manifest that the proposed network has superior performance and generalization. Compared to most of the blind denoising methods with additive white Gaussian noise, the proposed TGVLNet performs better in unseen noise level. It is noting that we train the model only on the synthetic image of the signal dependent noise removal, and use the model to remove the noise of some images on two real datasets, i.e NC12 and Nam, the denoising results also presents much better visual quality and performance, which further verify the generalization and robustness of our method.
Similar content being viewed by others
References
Arbelaez P, Fowlkes C, Martin D (2007) The Berkeley segmentation dataset and benchmark. Computer Science Department, Berkeley University [Online]. Available: http://www.eecs.berkeley.edu/Research/Projects/CS/vision/bsds
Bredies K, Dong Y, Hintermüller M. (2013) Spatially dependent regularization parameter selection in total generalized variation models for image restoration. Int J Comput Math 90(1):109–123
Buades A, Coll B, Morel JM (2005) A non-local algorithm for image denoising. In: IEEE Computer society conference on computer vision and pattern recognition (CVPR’05), vol 2, pp 60–65, IEEE
Burger HC, Schuler CJ, Harmeling S (2012) Image denoising: can plain neural networks compete with bm3d?. In: IEEE Conference on computer vision and pattern recognition, pp 2392–2399, IEEE
Chen Y, Pock T (2016) Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans Pattern Anal Mach Intell 39(6):1256–1272
Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Color image denoising via sparse 3d collaborative filtering with grouping constraint in luminance-chrominance space. In: IEEE International conference on image processing, vol 1, pp I–313, IEEE
Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans Image Process 16(8):2080–2095
Dong C, Loy CC, He K, Tang X (2015) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
Du H (2019) Image denoising algorithm based on nonlocal regularization sparse representation IEEE Sensors Journal
Elad M, Aharon M (2006) Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image Process 15(12):3736–3745
Getreuer P (2012) Rudin-osher-fatemi total variation denoising using split bregman. Image Processing On Line 2:74–95
Gu S, Zhang L, Zuo W, Feng X (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
Guo S, Yan Z, Zhang K, Zuo W, Zhang L (2019) Toward convolutional blind denoising of real photographs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1712–1722
Jain V, Seung S (2009) Natural image denoising with convolutional networks. In: Advances in neural information processing systems, pp 769–776
Lai R, Mo Y, Liu Z, Guan J (2019) Local and nonlocal steering kernel weighted total variation model for image denoising. Symmetry 11(3):329
Lebrun M, Colom M, Morel JM (2015) The noise clinic: a blind image denoising algorithm. Image Processing On Line 5:1–54
Lefkimmiatis S (2018) Universal denoising networks: a novel cnn architecture for image denoising. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3204–3213
Liu X, Tanaka M, Okutomi M (2014) Practical signal-dependent noise parameter estimation from a single noisy image. IEEE Trans Image Process 23(10):4361–4371
Loui A, Luo J, Chang SF, Ellis D, Jiang W, Kennedy L, Lee K, Yanagawa A (2007) Kodak’s consumer video benchmark data set: concept definition and annotation. In: Proceedings of the international workshop on Workshop on multimedia information retrieval, pp 245–254, ACM
Ma K, Duanmu Z, Wu Q, Wang Z, Yong H, Li H, Zhang L (2016) Waterloo exploration database: new challenges for image quality assessment models. IEEE Trans Image Process 26(2):1004–1016
Mairal J, Elad M, Sapiro G (2007) Sparse representation for color image restoration. IEEE Trans Image Process 17(1):53–69
Mao X, Shen C, Yang YB (2016) Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Advances in neural information processing systems, pp 2802–2810
Martin D, Fowlkes C, Tal D, Malik J, et al. (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: IEEE International conference on computer vision. Iccv vancouver
Nam S, Hwang Y, Matsushita Y, Joo Kim S (2016) A holistic approach to cross-channel image noise modeling and its application to image denoising. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1683–1691
Quan Y, Chen Y, Shao Y, Teng H, Xu Y, Ji H (2021) Image denoising using complex-valued deep cnn. Pattern Recogn 111:107–639. https://doi.org/10.1016/j.patcog.2020.107639
Shahdoosti HR, Rahemi Z (2019) Edge-preserving image denoising using a deep convolutional neural network. Signal Process 159:20–32
Shen Y, Liu Q, Lou S, Hou YL (2017) Wavelet-based total variation and nonlocal similarity model for image denoising. IEEE Signal Process Lett 24(6):877–881
Singh G, Mittal A, Aggarwal N (2020) Resdnn: deep residual learning for natural image denoising. IET Image Process 14(11):2425–2434. https://doi.org/10.1049/iet-ipr.2019.0623
Tai Y, Yang J, Liu X, Xu C (2017) Memnet: a persistent memory network for image restoration. In: Proceedings of the IEEE international conference on computer vision, pp 4539–4547
Tian C, Xu Y, Li Z, Zuo W, Fei L, Liu H (2020) Attention-guided cnn for image denoising. Neural Netw 124:117–129. https://doi.org/10.1016/j.neunet.2019.12.024
Tian C, Xu Y, Zuo W (2020) Image denoising using deep cnn with batch renormalization. Neural Netw 121:461–473. https://doi.org/10.1016/j.neunet.2019.08.022
Tian C, Xu Y, Zuo W, Du B, Lin CW, Zhang D (2021) Designing and training of a dual cnn for image denoising. Knowl-Based Syst 226:106–949. https://doi.org/10.1016/j.knosys.2021.106949
Wali S, Zhang H, Chang H, Wu C (2019) A new adaptive boosting total generalized variation (tgv) technique for image denoising and inpainting. J Vis Commun Image Represent 59:39–51
Xie J, Xu L, Chen E (2012) Image denoising and inpainting with deep neural networks. In: Advances in neural information processing systems, pp 341–349
xu Y, Tian C, Fei L, Wang J, Jie W, Luo N (2019) Enhanced cnn for image denoising CAAI Transactions on Intelligence Technology, vol 4 https://doi.org/10.1049/trit.2018.1054
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Trans Image Process 26(7):3142–3155
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
Zhang L, Wu X, Buades A, Li X (2011) Color demosaicking by local directional interpolation and nonlocal adaptive thresholding. J Electron Imaging 20(2):023–016
Zhang X, Liu J, Lu Y, Dong B (2019) Dynamically unfolding recurrent restorer: a moving endpoint control method for image restoration. In: 7Th international conference on learning representations, ICLR
Zhao H, Shao W, Bao B, Li H (2019) A simple and robust deep convolutional approach to blind image denoising. In: Proceedings of the IEEE international conference on computer vision workshops, pp 0–0
Zhu J, Li K, Hao B (2019) Restoration of remote sensing images based on nonconvex constrained high-order total variation regularization. J Appl Remote Sens 13(2):022–006
Zuo C, Jovanov L, Luong HQ, Goossens B, Philips W, Liu Y, Zhang M (2015) Rotation invariant similarity measure for non-local self-similarity based image denoising. In: IEEE International conference on image processing (ICIP), pp 1618–1622, IEEE
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was supported by the National Natural Science Foundation of China under Grant No.61471313 and Hebei Natural Science Foundation F2019203318.
Rights and permissions
About this article
Cite this article
Xiaohua, Z., Qiusheng, L. & Dan, Z. Total generalized variational-liked network for image denoising. Appl Intell 53, 9650–9667 (2023). https://doi.org/10.1007/s10489-022-03717-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03717-8