Gabor-based learnable sparse representation for self-supervised denoising

TL;DR

This paper introduces a Gabor-based learnable sparse representation network that enhances self-supervised denoising by embedding physics-inspired filters, eliminating the need for clean training labels and improving interpretability.

Contribution

It proposes a novel Gabor filter-based network that incorporates physics information for self-supervised denoising, addressing limitations of traditional supervised methods.

Findings

Effective in suppressing pseudo-random noise and ground roll

Validated on both synthetic and real data

Improves interpretability and self-supervision in denoising

Abstract

Traditional supervised denoising networks learn network weights through "black box" (pixel-oriented) training, which requires clean training labels. The uninterpretability nature of such denoising networks in addition to the requirement for clean data as labels limits their applicability in real case scenarios. Deep unfolding methods unroll an optimization process into Deep Neural Networks (DNNs), improving the interpretability of networks. Also, modifiable filters in DNNs allow us to embed the physics information of the desired signals to be extracted, in order to remove noise in a self-supervised manner. Thus, we propose a Gabor-based learnable sparse representation network to suppress different noise types in a self-supervised fashion through constraints/bounds applied to the parameters of the Gabor filters of the network during the training stage. The effectiveness of the proposed method was demonstrated on two noise type examples, pseudo-random noise and ground roll, on synthetic and real data.