Image Denoising Using Very Deep Fully Convolutional Encoder-Decoder Networks with Symmetric Skip Connections

Image denoising is a long-standing problem in computer vision and image processing, as well as a test bed for low-level image modeling algorithms. In this paper, we propose a very deep encoding-decoding framework for image denoising. Instead of using image priors, the proposed framework learns end-to-end fully convolutional mappings from noisy images to the clean ones. The network is composed of multiple layers of convolution and de-convolution operators. With the observation that deeper networks improve denoising performance, we propose to use significantly deeper networks than those employed previously for low-level image processing tasks such as denoising. We propose to symmetrically link convolutional and de-convolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum. From the image processing point of view, those symmetric connections help preserve image details.

[1]  Stefan Harmeling,et al.  Image denoising: Can plain neural networks compete with BM3D? , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[3]  Lei Zhang,et al.  Weighted Nuclear Norm Minimization with Application to Image Denoising , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Yair Weiss,et al.  From learning models of natural image patches to whole image restoration , 2011, 2011 International Conference on Computer Vision.

[5]  David Zhang,et al.  Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  David L. Donoho,et al.  De-noising by soft-thresholding , 1995, IEEE Trans. Inf. Theory.

[7]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[8]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[9]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[10]  Martin J. Wainwright,et al.  Image denoising using scale mixtures of Gaussians in the wavelet domain , 2003, IEEE Trans. Image Process..

[11]  Lei Zhang,et al.  Nonlocally Centralized Sparse Representation for Image Restoration , 2013, IEEE Transactions on Image Processing.

[12]  Wotao Yin,et al.  An Iterative Regularization Method for Total Variation-Based Image Restoration , 2005, Multiscale Model. Simul..

[13]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[14]  Seunghoon Hong,et al.  Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation , 2015, NIPS.

[15]  한보형,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015 .

[16]  Wen Gao,et al.  Image denoising via adaptive soft-thresholding based on non-local samples , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[18]  Shiguang Shan,et al.  Deep Network Cascade for Image Super-resolution , 2014, ECCV.

[19]  Jürgen Schmidhuber,et al.  Training Very Deep Networks , 2015, NIPS.

[20]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[21]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.

[22]  H. Sebastian Seung,et al.  Natural Image Denoising with Convolutional Networks , 2008, NIPS.

[23]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[24]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[25]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[26]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[28]  Minh N. Do,et al.  Wavelet-based texture retrieval using generalized Gaussian density and Kullback-Leibler distance , 2002, IEEE Trans. Image Process..

[29]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Peyman Milanfar,et al.  Clustering-Based Denoising With Locally Learned Dictionaries , 2009, IEEE Transactions on Image Processing.

[31]  Lei Zhang,et al.  External Patch Prior Guided Internal Clustering for Image Denoising , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).