Truncated Weighted Nuclear Norm Regularization and Sparsity for Image Denoising

The attribute of signal sparsity is widely used to sparse representaion. The existing nuclear norm minimization and weighted nuclear norm minimization may achieve a suboptimal in real application with the inaccurate approximation of rank function. This paper presents a novel denoising method that pr...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Image Processing (ICIP) pp. 1825 - 1829
Main Authors Zhang, MingYan, Zhang, Mingli, Zhao, Feng, Zhang, Fan, Liu, Yepeng, Evans, Alan
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.10.2023
Subjects
Adaptation models
Image denoising
low rank
Minimization
Noise reduction
Thresholding (Imaging)
TWNN
Visualization
Wavelet domain
wavelet domain sparsity
Wavelet transforms
Online AccessGet full text

Cover

More Information
Summary:The attribute of signal sparsity is widely used to sparse representaion. The existing nuclear norm minimization and weighted nuclear norm minimization may achieve a suboptimal in real application with the inaccurate approximation of rank function. This paper presents a novel denoising method that preserves fine structures in the image by imposing L 1 norm constraints on the wavelet transform coefficients and low rank on high-frequency components of group similar patches. An efficient proximal operator of Truncated Weighted Nuclear Norm (TWNN) is proposed to accurately recover the underlying high-frequency components of low rank patches. By combining a wavelet domain sparse preservation prior with TWNN, the proposed method significantly improves the reconstruction accuracy, leading to a higher PSNR/SSIM and visual quality than state of the art approaches.
DOI:10.1109/ICIP49359.2023.10221971