Abstract
Many image denoising methods achieve state-of-the-art performance with little consideration of computation efficiency. With the popularity of high-definition imaging devices, these denoising methods do not scale well to the high-definition images. Therefore, a fast image denoising method is proposed to meet the demand of processing high-definition images. Based on the analysis of the distribution of the distance \(dist_{rs}\) between the similar patches and their reference patches from a semantic aspect, the large \(dist_{rs}\)s was found to occur while their contribution to the overall distribution was small. Therefore, the nonlocal filters was replaced in trainable non-local reaction diffusion (TNLRD) with local filters. For image with \(4096 \times 4096\) resolution, the proposed method runs about 6 times faster than TNLRD via a single-thread CPU implementation. And the GPU implementation of the proposed method is about 10 times faster than the CPU implementation. Furthermore, the proposed model achieves competing denoising performance compared with TNLRD in terms of PSNR and SSIM.
P. Qiao and W. Sun—Equally contributed.
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
Similar content being viewed by others
Notes
- 1.
The values of the parameters are set to the same as those in TNLRD and other nonlocal methods using k Nearest Neighbors (kNN).
References
Aharon, M., Elad, M., Bruckstein, A.: K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Sig. Process. 54(11), 4311 (2006)
Black, M., Sapiro, G., Marimont, D., Heeger, D.: Robust anisotropic diffusion and sharpening of scalar and vector images. In: Proceedings of International Conference on Image Processing, vol. 1, pp. 263–266. IEEE (1997)
Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 60–65 (2005)
Chen, Y.: Notes on diffusion networks. arXiv preprint arXiv: 1503.05768 (2015)
Chen, Y., Yu, W., Pock, T.: On learning optimized reaction diffusion processes for effective image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 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. 16(8), 2080–2095 (2007)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009 (2009)
Dong, W., Zhang, L., Shi, G., Li, X.: Nonlocally centralized sparse representation for image restoration. IEEE Trans. Image Process. 22(4), 1620–1630 (2013)
Gu, S., Zhang, L., Zuo, W., Feng, X.: Weighted nuclear norm minimization with application to image denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2862–2869 (2014)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Math. Program. 45(1), 503–528 (1989)
Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Non-local sparse models for image restoration. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2272–2279. IEEE (2009)
Mao, X., Shen, C., Yang, Y.B.: Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Advances in Neural Information Processing Systems, pp. 2802–2810 (2016)
Miller, G.A., Beckwith, R., Fellbaum, C., Gross, D., Miller, K.J.: Introduction to WordNet: an on-line lexical database. Int. J. Lexicogr. 3(4), 235–244 (1990)
Qiao, P., Dou, Y., Feng, W., Li, R., Chen, Y.: Learning non-local image diffusion for image denoising. In: Proceedings of the 2017 ACM on Multimedia Conference, pp. 1847–1855. ACM (2017)
Roth, S., Black, M.J.: Fields of experts. Int. J. Comput. Vis. 82(2), 205–229 (2009)
Schmidt, U., Roth, S.: Shrinkage fields for effective image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2774–2781 (2014)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Sun, J., Tappen, M.F.: Learning non-local range Markov random field for image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2745–2752 (2011)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Weickert, J.: Anisotropic Diffusion in Image Processing, vol. 1. Teubner, Stuttgart (1998)
Xu, J., Zhang, L., Zuo, W., Zhang, D., Feng, X.: Patch group based nonlocal self-similarity prior learning for image denoising. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 244–252 (2015)
Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26(7), 3142–3155 (2017)
Zhang, K., Zuo, W., Gu, S., Zhang, L.: Learning deep CNN denoiser prior for image restoration. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2 (2017)
Zhang, K., Zuo, W., Zhang, L.: FFDNet: toward a fast and flexible solution for CNN based image denoising. IEEE Trans. Image Process. 27, 4608–4622 (2018)
Zontak, M., Irani, M.: Internal statistics of a single natural image. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 977–984. IEEE (2011)
Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 479–486. IEEE (2011)
Acknowledgements
This work was supported by the National Key Research and Development Program of China under the Grant No. 2018YFB1003405, and National Natural Science Foundation of China under the Grant No. 61732018.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Qiao, P., Sun, W., Dou, Y., Li, R. (2019). Fast Nonlocal Diffusion by Stacking Local Filters for Image Denoising. In: Mao, R., Wang, H., Xie, X., Lu, Z. (eds) Data Science. ICPCSEE 2019. Communications in Computer and Information Science, vol 1059. Springer, Singapore. https://doi.org/10.1007/978-981-15-0121-0_6
Download citation
DOI: https://doi.org/10.1007/978-981-15-0121-0_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0120-3
Online ISBN: 978-981-15-0121-0
eBook Packages: Computer ScienceComputer Science (R0)