Learning a Generic Adaptive Wavelet Shrinkage Function for Denoising

TL;DR

This paper introduces a new adaptive wavelet shrinkage function for image denoising that combines the transparency of classical methods with the performance of learning-based models, outperforming existing functions.

Contribution

A novel, smooth, and compact wavelet shrinkage function with only two parameters, adaptable to noise levels and wavelet scales, inspired by nonlinear diffusion.

Findings

Outperforms classical shrinkage functions significantly

Enhances image structures by amplifying wavelet coefficients

Adapts to noise standard deviation and wavelet scales

Abstract

The rise of machine learning in image processing has created a gap between trainable data-driven and classical model-driven approaches: While learning-based models often show superior performance, classical ones are often more transparent. To reduce this gap, we introduce a generic wavelet shrinkage function for denoising which is adaptive to both the wavelet scales as well as the noise standard deviation. It is inferred from trained results of a tightly parametrised function which is inherited from nonlinear diffusion. Our proposed shrinkage function is smooth and compact while only using two parameters. In contrast to many existing shrinkage functions, it is able to enhance image structures by amplifying wavelet coefficients. Experiments show that it outperforms classical shrinkage functions by a significant margin.