Rethinking the CSC Model for Natural Images

Sparse representation with respect to an overcomplete dictionary is often used when regularizing inverse problems in signal and image processing. In recent years, the Convolutional Sparse Coding (CSC) model, in which the dictionary consists of shift invariant filters, has gained renewed interest. While this model has been successfully used in some image processing problems, it still falls behind traditional patch-based methods on simple tasks such as denoising. In this work we provide new insights regarding the CSC model and its capability to represent natural images, and suggest a Bayesian connection between this model and its patch-based ancestor. Armed with these observations, we suggest a novel feed-forward network that follows an MMSE approximation process to the CSC model, using strided convolutions. The performance of this supervised architecture is shown to be on par with state of the art methods while using much fewer parameters.

[1]  Guillermo Sapiro,et al.  Online dictionary learning for sparse coding , 2009, ICML '09.

[2]  Gordon Wetzstein,et al.  Fast and flexible convolutional sparse coding , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Lei Zhang,et al.  Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization , 2010, IEEE Transactions on Image Processing.

[4]  Michael Elad,et al.  Sparse and Redundant Representations - From Theory to Applications in Signal and Image Processing , 2010 .

[5]  Raja Giryes,et al.  Learned Convolutional Sparse Coding , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Jeffrey A. Fessler,et al.  Convolutional Dictionary Learning: Acceleration and Convergence , 2017, IEEE Transactions on Image Processing.

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

[8]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[9]  Yoram Bresler,et al.  MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning , 2011, IEEE Transactions on Medical Imaging.

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

[11]  Brendt Wohlberg,et al.  Convolutional Dictionary Learning: A Comparative Review and New Algorithms , 2017, IEEE Transactions on Computational Imaging.

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

[13]  Pascal Frossard,et al.  Dictionary learning: What is the right representation for my signal? , 2011 .

[14]  Thomas S. Huang,et al.  Deep Networks for Image Super-Resolution with Sparse Prior , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[15]  Rabab Kreidieh Ward,et al.  Image Fusion With Convolutional Sparse Representation , 2016, IEEE Signal Processing Letters.

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

[17]  Feng Liu,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries in Wavelet Domain , 2009, 2009 Fifth International Conference on Image and Graphics.

[18]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Lei Zhang,et al.  FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising , 2017, IEEE Transactions on Image Processing.

[20]  Michael Elad,et al.  A Plurality of Sparse Representations Is Better Than the Sparsest One Alone , 2009, IEEE Transactions on Information Theory.

[21]  Rémi Gribonval,et al.  Sparse Representations in Audio and Music: From Coding to Source Separation , 2010, Proceedings of the IEEE.

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

[23]  Yann LeCun,et al.  Learning Fast Approximations of Sparse Coding , 2010, ICML.

[24]  Michael Elad,et al.  A Local Block Coordinate Descent Algorithm for the Convolutional Sparse Coding Model , 2018, ArXiv.

[25]  Yann LeCun,et al.  Discriminative Recurrent Sparse Auto-Encoders , 2013, ICLR.

[26]  Kjersti Engan,et al.  Method of optimal directions for frame design , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[27]  Brendt Wohlberg,et al.  Efficient Algorithms for Convolutional Sparse Representations , 2016, IEEE Transactions on Image Processing.

[28]  Erik G. Larsson,et al.  Linear Regression With a Sparse Parameter Vector , 2007, IEEE Transactions on Signal Processing.

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

[30]  Philip Schniter,et al.  Fast Bayesian Matching Pursuit: Model Uncertainty and Parameter Estimation for Sparse Linear Models , 2009 .

[31]  Thomas S. Huang,et al.  Non-Local Recurrent Network for Image Restoration , 2018, NeurIPS.

[32]  Balas K. Natarajan,et al.  Sparse Approximate Solutions to Linear Systems , 1995, SIAM J. Comput..

[33]  Yann LeCun,et al.  Convolutional Matching Pursuit and Dictionary Training , 2010, ArXiv.

[34]  Lei Zhang,et al.  Convolutional Sparse Coding for Image Super-Resolution , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[35]  Brendt Wohlberg,et al.  Fast convolutional sparse coding with separable filters , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[36]  Michael Elad,et al.  Convolutional Dictionary Learning via Local Processing , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Michael Elad,et al.  MMSE Approximation For Sparse Coding Algorithms Using Stochastic Resonance , 2018, IEEE Transactions on Signal Processing.

[38]  Adrian S. Lewis,et al.  Image compression using the 2-D wavelet transform , 1992, IEEE Trans. Image Process..

[39]  Brendt Wohlberg,et al.  Sparse Overcomplete Denoising: Aggregation Versus Global Optimization , 2017, IEEE Signal Processing Letters.

[40]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[41]  Michael Elad,et al.  Expected Patch Log Likelihood with a Sparse Prior , 2014, EMMCVPR.

[42]  D. Donoho,et al.  Basis pursuit , 1994, Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers.

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

[44]  Guillermo Sapiro,et al.  Non-local sparse models for image restoration , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[45]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[46]  Brendt Wohlberg.  Convolutional Sparse Coding with Overlapping Group Norms , 2017, ArXiv.

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

[48]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[49]  Michael Elad,et al.  Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding , 2017, IEEE Transactions on Signal Processing.

[50]  Michael Elad,et al.  Variations on the CSC model , 2018 .

[51]  Rebecca Willett,et al.  Poisson Noise Reduction with Non-local PCA , 2012, Journal of Mathematical Imaging and Vision.

[52]  Lei Zhang,et al.  Waterloo Exploration Database: New Challenges for Image Quality Assessment Models , 2017, IEEE Transactions on Image Processing.

[53]  Yunjin Chen,et al.  Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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