Multi-Modal Deep Convolutional Dictionary Learning for Image Denoising



Zhonggui Sun1,2, Mingzhu Zhang1, Huichao Sun1, Jie Li2,  Tingting Liu3, Xinbo Gao3,*

1. School of Mathematical Sciences, Liaocheng University, Liaocheng,252000, China

2. School of Electronic Engineering, Xidian University, Xi’an, 710071, China

3. Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
　

Abstract

Leveraging the capabilities of traditional dictionary learning (DicL) and drawing upon the success of deep neural networks (DNNs), the recently proposed framework of deep convolutional dictionary learning (DCDicL) has exhibited remarkable behaviors in image denoising.   However, the application of the DCDicL method is confined to single modality scenarios, whereas the images in practice often originate from diverse modalities. In this paper, to broaden the application scope of the DCDicL method, we design a multi-modal version of it, dubbed MMDCDicL. Specifically, within the mathematical model of MMDCDicL, we adopt an analytical approach to tackle the sub-problem linked to the guidance modality, harnessing its inherent reliability. Meanwhile, like in DCDicL, we utilize a network-based learning approach for the noisy modality to extract trustworthy information from the data. Based on the solution, we establish an interpretable network structure for MMDCDicL. Additionally, wherein, we design a multi-kernel channel attention block (MKCAB) in the structure to efficiently integrate the information from diverse modalities. Experimental results suggest that MMDCDicL can reconstruct higher-quality outcomes both quantitatively and perceptually. The code of MMDCDicL is accessible at http://www.diplab.net/lunwen/mmdcdicl.htm.
 
　

Paper

Z. Sun, M. Zhang, H. Sun, J. Li, T. Liu，X. Gao. Multi-Modal Deep Convolutional Dictionary Learning for Image Denoising.  Neurocomputing，vol.562, pp.1-11, 2023.  code

　

Architecture

　

　

Visualization Results

　

　

　

Theories

　

　

---------------------------------------------------------------------------------------------------

　

　

---------------------------------------------------------------------------------------------------