Abstract
Image denoising is one of the most important tasks in image processing. In this paper, we propose a new method called Non-ParaMetric Alternating Direction Method of Multiplier (ADMM) algorithm (NPM-ADMM). We utilize the standard ADMM algorithm to solve the noisy image model and update the parameters via back propagation by minimizing the loss function. In contrast to the previous methods which are required to set the parameters carefully to approach better results, the proposed method can automatically learn the related parameters without the need of manually specifying. Furthermore, the filter coefficients and the nonlinear function in the regularization term are also learned together with the parameters, rather than fixed. Experiments on image denoising demonstrate our superior results with fast convergence speed and high restoration quality.
This work was supported by National Natural Science Foundation of China (NSFC) under Grant 61702078, and by the Fundamental Research Funds for the Central Universities.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barbu, A.: Training an active random field for real-time image denoising. IEEE Trans. Image Process. (TIP) 18(11), 2451–2462 (2009)
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3(1), 1–122 (2011)
Boyle, R., Thomas, R.: Computer Vision: A First Course. Blackwell Scientific Publications (1988)
Bredies, K., Kunisch, K., Pock, T.: Total generalized variation. SIAM J. Imag. Sci. 3(3), 492–526 (2010)
Chan, S., Wang, X., Elgendy, O.: Plug-and-play admm for image restoration: fixed-point convergence and applications. Proc. IEEE Trans. Comput. Imaging 3(1), 84–98 (2016)
Chen, Y., Yu, W., Pock, T.: On learning optimized reaction diffusion processes for effective image restoration. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5261–5269 (2015)
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans. Image Process. (TIP) 16(8), 2080–2095 (2007)
Elad, M., Matalon, B., Zibulevsky, M.: Image denoising with shrinkage and redundant repersentations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1924–1931 (2006)
Gao, Q., Roth, S.: How well do filter-based mrfs model natural images? In: Proceedings of German Association for Pattern Recognition (DAGM), pp. 62–72 (2012)
Jia, Y., Darrell, T.: Heavy-tailed sistances for gradient based image descriptors. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), pp. 397–405 (2011)
Kim, Y., Jung, H., Min, D., Sohn, K.: Deeply aggregated alternating minimization for image restoration. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 284–292 (2017)
Krishnan, D., Fergus, R.: Fast image deconvolution using hyper-laplacian priors. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), pp. 1033–1041 (2009)
Lin, Z., Chen, M., Ma, Y.: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv preprint arXiv:1009.5055 (2010)
Liu, D., Nocedal, J.: On the limited memory bfgs method for large scale optimization. Proc. Math. Program. 45(1–3), 503–528 (1989)
Martin, D., Black, M.J.: Fields of experts. Int. J. Comput. Vis. (IJCV) 82(2), 205–229 (2009)
Meinhardt, T., Moeller, M., Hazirbas, C., Cremers, D.: Learning proximal operators: using denoising networks for regularizing inverse imaging problems. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 1781–1790 (2017)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. Proc. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 629–639 (1990)
Poor, H.V.: An Introduction to Signal Detection and Estimation, 2nd edn. Springer, Heidelberg (1998). https://doi.org/10.1007/978-1-4757-2341-0
Portilla, J., Strela, V., Wainwright, M., Simoncelli, E.: Image denoising using scale mixtures of gaussians in the wavelet domain. IEEE Trans. Image Process. (TIP) 12(11), 1338–1351 (2003)
Schmidt, M.: minfunc (2013). http://mloss.org/software/view/529.html
Schmidt, U., Roth, S.: Shrinkage fields for effective image restoration. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3791–3799 (2015)
Taylor, G., Burmeister, R., Xu, Z., Singh, B., Patel, A., Goldstein, T.: Training neural networks without gradients: a scalable admm approach. In: Proceedings of International Conference on International Conference on Machine Learning, pp. 2722–2731 (2016)
Vert, J.P., Tsuda, K., Scholkopf, B.: A primer on kernel methods. In: Proceedings of Kernel Methods in Computational, pp. 35–70 (2004)
Wang, H., Banerjee, A., Luo, Z.: Parallel direction method of multipliers. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), pp. 181–189 (2014)
Wang, Y., Li, K., Yang, J., Ye, X.: Intrinsic decomposition from a single RGB-D image with sparse and non-local priors. In: Proceedings of IEEE International Conference on Multimedia & Expo (ICME), pp. 1201–1206 (2017)
Wang, Y., Yang, J., Yin, W., Zhang, Y.: A ner alternating minimization algorithm for total variation image reconstruction. SIAM J. Imag. Sci. 1(3), 248–272 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Ye, X., Zhang, M., Yan, Q., Fan, X., Luo, Z. (2018). Image Denoising Based on Non-parametric ADMM Algorithm. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11165. Springer, Cham. https://doi.org/10.1007/978-3-030-00767-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-00767-6_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00766-9
Online ISBN: 978-3-030-00767-6
eBook Packages: Computer ScienceComputer Science (R0)