Abstract
A deep learning approach to blind denoising of images without complete knowledge of the noise statistics is considered. We propose DN-ResNet, which is a deep convolutional neural network (CNN) consisting of several residual blocks (ResBlocks). With cascade training, DN-ResNet is more accurate and more computationally efficient than the state of art denoising networks. An edge-aware loss function is further utilized in training DN-ResNet, so that the denoising results have better perceptive quality compared to conventional loss function. Next, we introduce the depthwise separable DN-ResNet (DS-DN-ResNet) utilizing the proposed Depthwise Seperable ResBlock (DS-ResBlock) instead of standard ResBlock, which has much less computational cost. We propose cascade evolution of DS-DN-ResNet from DN-ResNet by incrementally transforming the ResBlocks to DS-ResBlocks, while building on the previous training. As a result, high accuracy and good computational efficiency are achieved concurrently. Whereas previous state of art deep learning methods focused on denoising either Gaussian or Poisson corrupted images, we consider denoising images having the more practical Poisson with additive Gaussian noise as well. The results show that DN-ResNets are more efficient, robust, and perform better denoising than current state of art deep learning methods, as well as the popular variants of the BM3D algorithm, in cases of blind and non-blind denoising of images corrupted with Poisson, Gaussian or Poisson-Gaussian noise. Our network also works well for other image enhancement task such as compressed image restoration.
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
Notes
- 1.
In the quantitative evaluation, we show the PSNR/SSIM of the networks trained on y-channel only for fair comparison to existing work.
References
Azzari, L., Foi, A.: Variance stabilization for Noisy+Estimate combination in iterative Poisson denoising. IEEE Signal Process. Lett. 23(8), 1086–1090 (2016)
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 (2012)
Chen, Y., Pock, T.: Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1256–1272 (2017)
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)
Dong, W., Zhang, L., Shi, G., Li, X.: Nonlocally centralized sparse representation for image restoration. IEEE Trans. Image Process. 22(4), 1620–1630 (2013)
Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Foi, A., Trimeche, M., Katkovnik, V., Egiazarian, K.: Practical Poissonian-Gaussian noise modeling and fitting for single-image raw-data. IEEE Trans. Image Process. 17(10), 1737–1754 (2008)
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 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)
Workshop and challenge on learned image compression (CLIC) (2018). http://www.compression.cc/
Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (2017)
Makitalo, M., Foi, A.: Optimal inversion of the generalized Anscombe transformation for Poisson-Gaussian noise. IEEE Trans. Image Process. 22(1), 91–103 (2013)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: 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, vol. 2, pp. 416–423 (2001)
Remez, T., Litany, O., Giryes, R., Bronstein, A.M.: Deep class-aware image denoising. In: International Conference on Sampling Theory and Applications (2017)
Remez, T., Litany, O., Giryes, R., Bronstein, A.M.: Deep convolutional denoising of low-light images. arXiv:1701.01687 (2017)
Ren, H., El-Khamy, M., Lee, J.: Image super resolution based on fusing multiple convolution neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1050–1057. IEEE (2017)
Ren, H., El-Khamy, M., Lee, J.: CT-SRCNN: cascade trained and trimmed deep convolutional neural networks for image super resolution (2018)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetv 2: Inverted residuals and linear bottlenecks. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)
Schmidt, U., Jancsary, J., Nowozin, S., Roth, S., Rother, C.: Cascades of regression tree fields for image restoration. IEEE Trans. Pattern Anal. Mach. Intell. 38(4), 677–689 (2016)
Tai, Y., Yang, J., Liu, X.: Image super-resolution via deep recursive residual network (2017)
Tai, Y., Yang, J., Liu, X., Xu, C.: MemNet: a persistent memory network for image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4539–4547 (2017)
Theis, L., Shi, W., Cunningham, A., Huszár, F.: Lossy image compression with compressive autoencoders. arXiv:1703.00395 (2017)
Toderici, G., et al.: Full resolution image compression with recurrent neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5435–5443 (2017)
Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Boissonnat, J.D., et al. (eds.) Curves and Surfaces 2010. LNCS, vol. 6920, pp. 711–730. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-27413-8_47
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., Zhang, L.: FFDnet: toward a fast and flexible solution for CNN based image denoising. arXiv:1710.04026 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ren, H., El-khamy, M., Lee, J. (2019). DN-ResNet: Efficient Deep Residual Network for Image Denoising. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11365. Springer, Cham. https://doi.org/10.1007/978-3-030-20873-8_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-20873-8_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20872-1
Online ISBN: 978-3-030-20873-8
eBook Packages: Computer ScienceComputer Science (R0)