Image Denoising by Random Interpolation Average with Low-Rank Matrix Approximation

TL;DR

This paper introduces a novel image denoising technique that simultaneously addresses impulsive noise and Gaussian noise by combining low-rank matrix approximation, random sampling, and wavelet fusion, resulting in high-quality denoised images.

Contribution

It proposes a new denoising framework that effectively handles both impulsive and Gaussian noise using low-rank matrix approximation and wavelet fusion, preserving image structure.

Findings

Achieves clear denoised images with strong structural integrity.

Performs well in subjective visual quality and objective metrics.

Effectively suppresses both impulsive noise and Gaussian noise.

Abstract

With the wide deployment of digital image capturing equipment, the need of denoising to produce a crystal clear image from noisy capture environment has become indispensable. This work presents a novel image denoising method that can tackle both impulsive noise, such as salt and pepper noise (SAPN), and additive white Gaussian noise (AWGN), such as hot carrier noise from CMOS sensor, at the same time. We propose to use low-rank matrix approximation to form the basic denoising framework, as it has the advantage of preserving the spatial integrity of the image. To mitigate the SAPN, the original noise corrupted image is randomly sampled to produce sampled image sets. Low-rank matrix factorization method (LRMF) via alternating minimization denoising method is applied to all sampled images, and the resultant images are fused together via a wavelet fusion with hard threshold denoising. Since the sampled image sets have independent but identical noise property, the wavelet fusion serves as the effective mean to remove the AWGN, while the LRMF method suppress the SAPN. Simulation results are presented which vividly show the denoised images obtained by the proposed method can achieve crystal clear image with strong structural integrity and showing good performance in both subjective and objective metrics.