Advertisement

Deep Boosting for Image Denoising

  • Chang Chen
  • Zhiwei XiongEmail author
  • Xinmei Tian
  • Feng Wu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11215)

Abstract

Boosting is a classic algorithm which has been successfully applied to diverse computer vision tasks. In the scenario of image denoising, however, the existing boosting algorithms are surpassed by the emerging learning-based models. In this paper, we propose a novel deep boosting framework (DBF) for denoising, which integrates several convolutional networks in a feed-forward fashion. Along with the integrated networks, however, the depth of the boosting framework is substantially increased, which brings difficulty to training. To solve this problem, we introduce the concept of dense connection that overcomes the vanishing of gradients during training. Furthermore, we propose a path-widening fusion scheme cooperated with the dilated convolution to derive a lightweight yet efficient convolutional network as the boosting unit, named Dilated Dense Fusion Network (DDFN). Comprehensive experiments demonstrate that our DBF outperforms existing methods on widely used benchmarks, in terms of different denoising tasks.

Notes

Acknowledgements

We acknowledge funding from National Key R&D Program of China under Grant 2017YFA0700800, and Natural Science Foundation of China under Grants 61671419 and 61425026.

References

  1. 1.
    Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: IEEE International Conference on Computer Vision (ICCV), pp. 479–486 (2011)Google Scholar
  2. 2.
    Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 60–65, June 2005Google Scholar
  3. 3.
    Buades, A., Coll, B., Morel, J.: Nonlocal image and movie denoising. Int. J. Comput. Vis. (IJCV) 76(2), 123–139 (2008)CrossRefGoogle Scholar
  4. 4.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Non-local sparse models for image restoration. In: IEEE International Conference on Computer Vision (ICCV), pp. 2272–2279 (2009)Google Scholar
  5. 5.
    Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. Image Process. 15(12), 3736–3745 (2006)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Dong, W., Zhang, L., Shi, G., Li, X.: Nonlocally centralized sparse representation for image restoration. IEEE Trans. Image Process. 22(4), 1620–1630 (2013)MathSciNetCrossRefGoogle Scholar
  7. 7.
    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)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Schmidt, U., Roth, S.: Shrinkage fields for effective image restoration. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2774–2781, June 2014Google Scholar
  9. 9.
    Gu, S., Zhang, L., Zuo, W., Feng, X.: Weighted nuclear norm minimization with application to image denoising. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2862–2869, June 2014Google Scholar
  10. 10.
    Burger, H.C., Schuler, C.J., Harmeling, S.: Image denoising: can plain neural networks compete with BM3D? In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2392–2399, June 2012Google Scholar
  11. 11.
    Chen, Y., Pock, T.: Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans. Patt. Anal. Mach. Intell. 39(6), 1256 (2017)CrossRefGoogle Scholar
  12. 12.
    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)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Remez, T., Litany, O., Giryes, R., Bronstein, A.M.: Deep class-aware image denoising. In: International Conference on Sampling Theory and Applications (SampTA), pp. 138–142, July 2017Google Scholar
  14. 14.
    Charest, M.R., Elad, M., Milanfar, P.: A general iterative regularization framework for image denoising. In: Conference on Information Sciences and Systems, pp. 452–457, March 2006Google Scholar
  15. 15.
    Milanfar, P.: A tour of modern image filtering: new insights and methods, both practical and theoretical. IEEE Sig. Process. Mag. 30(1), 106–128 (2013)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Talebi, H., Zhu, X., Milanfar, P.: How to SAIF-ly boost denoising performance. IEEE Trans. Image Process. 22(4), 1470–1485 (2013)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Romano, Y., Elad, M.: Boosting of image denoising algorithms. SIAM J. Imaging Sci. 8(2), 1187–1219 (2015)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269, July 2017Google Scholar
  19. 19.
    Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: International Conference on Learning Representations (ICLR) (2016)Google Scholar
  20. 20.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (ICML), pp. 448–456 (2015)Google Scholar
  21. 21.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, June 2016Google Scholar
  22. 22.
    Buades, A., Coll, B., Morel, J.M.: A review of image denoising algorithms, with a new one. SIAM J. Multiscale Model. Simul. 4(2), 490–530 (2005)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Han, S., Meng, Z., Khan, A.S., Tong, Y.: Incremental boosting convolutional neural network for facial action unit recognition. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems (NIPS), pp. 109–117. Curran Associates, Inc. (2016)Google Scholar
  24. 24.
    Moghimi, M., Saberian, M., Yang, J., Li, L.J., Vasconcelos, N., Belongie, S.: Boosted convolutional neural networks. In: British Machine Vision Conference (BMVC), pp. 24.1–24.13 (2016)Google Scholar
  25. 25.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: International Conference on Machine Learning (ICML), pp. 807–814 (2010)Google Scholar
  26. 26.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826, June 2016Google Scholar
  27. 27.
    Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1646–1654, June 2016Google Scholar
  28. 28.
    Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 636–644, July 2017Google Scholar
  29. 29.
    Roth, S., Black, M.J.: Fields of experts: a framework for learning image priors. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 860–867, June 2005Google Scholar
  30. 30.
    Dong, C., Deng, Y., Loy, C.C., Tang, X.: Compression artifacts reduction by a deep convolutional network. In: IEEE International Conference on Computer Vision (ICCV), pp. 576–584, December 2015Google Scholar
  31. 31.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR), vol. 5 (2015)Google Scholar
  32. 32.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE International Conference on Computer Vision (ICCV), pp. 1026–1034, December 2015Google Scholar
  33. 33.
    Vemulapalli, R., Tuzel, O., Liu, M.Y.: Deep Gaussian conditional random field network: a model-based deep network for discriminative denoising. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4801–4809, June 2016Google Scholar
  34. 34.
    Lefkimmiatis, S.: Non-local color image denoising with convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5882–5891, July 2017Google Scholar
  35. 35.
    Kim, Y., Jung, H., Min, D., Sohn, K.: Deeply aggregated alternating minimization for image restoration. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 284–292, July 2017Google Scholar
  36. 36.
    Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Color image denoising via sparse 3D collaborative filtering with grouping constraint in luminance-chrominance space. In: IEEE International Conference on Image Processing (ICIP), vol. 1, I-313–I-316, September 2007Google Scholar
  37. 37.
    Shi, Z., Chen, C., Xiong, Z., Liu, D., Wu, F.: HSCNN+: advanced CNN-based hyperspectral recovery from RGB images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2018Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Chang Chen
    • 1
  • Zhiwei Xiong
    • 1
    Email author
  • Xinmei Tian
    • 1
  • Feng Wu
    • 1
  1. 1.University of Science and Technology of ChinaHefeiChina

Personalised recommendations