Loss functions for denoising compressed images: a comparative study

This paper faces the problem of denoising compressed images, obtained through a quantization in a known basis. The denoising is formulated as a variational inverse problem regularized by total variation, the emphasis being placed on the data-fidelity term which measures the distance between the noisy observation and the reconstruction. The paper introduces two new loss functions to jointly denoise and dequantize the corrupted image, which fully exploit the knowledge about the compression process, i.e., the transform and the quantization steps. Several numerical experiments demonstrate the effectiveness of the proposed loss functions and compare their performance with two more classical ones.

[1]  Jacques Froment,et al.  Adapted Total Variation for Artifact Free Decompression of JPEG Images , 2005, Journal of Mathematical Imaging and Vision.

[2]  Michael K. Ng,et al.  Reducing Artifacts in JPEG Decompression Via a Learned Dictionary , 2014, IEEE Transactions on Signal Processing.

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

[4]  G. Moury,et al.  The new CCSDS image compression recommendation , 2005, 2005 IEEE Aerospace Conference.

[5]  Patrick L. Combettes,et al.  Signal Recovery by Proximal Forward-Backward Splitting , 2005, Multiscale Model. Simul..

[6]  Stephen P. Boyd,et al.  Compressed Sensing With Quantized Measurements , 2010, IEEE Signal Processing Letters.

[7]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1992 .

[8]  Andrea Vedaldi,et al.  Deep Image Prior , 2017, International Journal of Computer Vision.

[9]  Saïd Ladjal,et al.  Robust Multi-image Processing with Optimal Sparse Regularization , 2014, Journal of Mathematical Imaging and Vision.

[10]  Laurent Jacques,et al.  Dequantizing Compressed Sensing: When Oversampling and Non-Gaussian Constraints Combine , 2009, IEEE Transactions on Information Theory.

[11]  Patrick L. Combettes,et al.  Proximal Splitting Methods in Signal Processing , 2009, Fixed-Point Algorithms for Inverse Problems in Science and Engineering.

[12]  François Malgouyres,et al.  Minimizing the total variation under a general convex constraint for image restoration , 2002, IEEE Trans. Image Process..

[13]  Laurent D. Cohen,et al.  Non-local Regularization of Inverse Problems , 2008, ECCV.

[14]  Mila Nikolova,et al.  Efficient Minimization Methods of Mixed l2-l1 and l1-l1 Norms for Image Restoration , 2005, SIAM J. Sci. Comput..

[15]  I. Daubechies,et al.  An iterative thresholding algorithm for linear inverse problems with a sparsity constraint , 2003, math/0307152.

[16]  Yann Kerr,et al.  Sparsity-based restoration of SMOS images in the presence of outliers , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[17]  Jean-Michel Morel,et al.  A Nonlocal Bayesian Image Denoising Algorithm , 2013, SIAM J. Imaging Sci..

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

[19]  Jean-Michel Morel,et al.  The noise clinic: A universal blind denoising algorithm , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[20]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[21]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[22]  Ronald R. Coifman,et al.  Combining the Calculus of Variations and Wavelets for Image Enhancement , 2000 .

[23]  Mila Nikolova,et al.  Minimizers of Cost-Functions Involving Nonsmooth Data-Fidelity Terms. Application to the Processing of Outliers , 2002, SIAM J. Numer. Anal..