Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learning
This is an incremental review that synthesizes existing literature to highlight denoising's broad utility for researchers and practitioners in imaging, inverse problems, and machine learning.
The paper tackles the underappreciation of denoising's applications beyond noise removal by providing a clarifying perspective on denoisers and showcasing its evolution into an essential building block for complex tasks in imaging, inverse problems, and machine learning, with recent techniques nearing theoretical limits in some measures.
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.