Investigating Self-Supervised Image Denoising with Denaturation

TL;DR

This paper provides a theoretical and experimental analysis of a self-supervised image denoising algorithm that uses denatured data, revealing its effectiveness and guiding future improvements in denoising methods.

Contribution

It offers the first in-depth theoretical analysis of denatured data in self-supervised denoising and validates findings with numerical experiments.

Findings

The algorithm finds desired solutions with population risk.

Empirical performance aligns with theoretical predictions.

Training with denatured images is effective in practice.

Abstract

Self-supervised learning for image denoising problems in the presence of denaturation for noisy data is a crucial approach in machine learning. However, theoretical understanding of the performance of the approach that uses denatured data is lacking. To provide better understanding of the approach, in this paper, we analyze a self-supervised denoising algorithm that uses denatured data in depth through theoretical analysis and numerical experiments. Through the theoretical analysis, we discuss that the algorithm finds desired solutions to the optimization problem with the population risk, while the guarantee for the empirical risk depends on the hardness of the denoising task in terms of denaturation levels. We also conduct several experiments to investigate the performance of an extended algorithm in practice. The results indicate that the algorithm training with denatured images works, and the empirical performance aligns with the theoretical results. These results suggest several insights for further improvement of self-supervised image denoising that uses denatured data in future directions.