Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learning

TL;DR

This paper highlights the fundamental role of denoising as a versatile building block in imaging, inverse problems, and machine learning, emphasizing its evolving applications and recent breakthroughs.

Contribution

It provides a comprehensive overview and perspective on denoisers, their structure, properties, and expanding significance across various scientific and engineering domains.

Findings

Denoising techniques have achieved near-theoretical limits in imaging.

Denoising is increasingly used as a core component in complex tasks.

The applications of denoising extend beyond noise reduction to diverse fields.

Abstract

Denoising, the process of reducing random fluctuations in a signal to emphasize essential patterns, has been a fundamental problem of interest since the dawn of modern scientific inquiry. Recent denoising techniques, particularly in imaging, have achieved remarkable success, nearing theoretical limits by some measures. Yet, despite tens of thousands of research papers, the wide-ranging applications of denoising beyond noise removal have not been fully recognized. This is partly due to the vast and diverse literature, making a clear overview challenging. This paper aims to address this gap. We present a clarifying perspective on denoisers, their structure, and desired properties. We emphasize the increasing importance of denoising and showcase its evolution into an essential building block for complex tasks in imaging, inverse problems, and machine learning. Despite its long history, the community continues to uncover unexpected and groundbreaking uses for denoising, further solidifying its place as a cornerstone of scientific and engineering practice.