Revisiting Convolutional Sparse Coding for Image Denoising: From a Multi-Scale Perspective
Authors:
- 13 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 29 (10709908) , 1202-1206
Abstract
Recently, convolutional sparse coding (CSC) has shown great success in many image processing tasks, such as image super-resolution and image separation. However, it performs poorly in image denoising task. In this letter, we provide a new insight for CSC denoising by revisiting the CSC from a multi-scale perspective. We propose a multi-scale CSC model for image denoising. By unrolling the multi-scale solution into a learnable network, we obtain an interpretable lightweight multi-scale network, namely MCSCNet. Experimental results show that the proposed MCSCNet significantly advances the denoising performance, with an average PSNR improvement of 0.32 dB over the state-of-the-art (SOTA) CSC based method. In addition, our MCSCNet is on par with many SOTA deep learning based methods, with less network parameters and lower FLOPs. The ablation study also validates the effectiveness of the multi-scale CSC mechanism.Keywords
Funding Information
- National Natural Science Foundation of China (62001016, 62050175)
- Beijing Natural Science Foundation (JQ20020)
This publication has 26 references indexed in Scilit:
- Efficient Algorithms for Convolutional Sparse RepresentationsIEEE Transactions on Image Processing, 2015
- Single image super-resolution from transformed self-exemplars2015
- Weighted Nuclear Norm Minimization with Application to Image Denoising2014
- Non-Linear Direct Multi-Scale Image Enhancement Based on the Luminance and Contrast Masking Characteristics of the Human Visual SystemIEEE Transactions on Image Processing, 2013
- From learning models of natural image patches to whole image restoration2011
- Color demosaicking by local directional interpolation and nonlocal adaptive thresholdingJournal of Electronic Imaging, 2011
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002
- Atomic Decomposition by Basis PursuitSIAM Review, 2001
- Method of optimal directions for frame design1999