Sparsity-based denoising of photographic images: From model-based to data-driven

Abstract

What makes photographic images different from random noise? It has been hypothesized that sparsity is a key factor separating the class of photographic images from noise observations. Accordingly, sparse representations have been widely studied in the literature of image denoising in the past decades. In this chapter, we present a critical review of the most important ideas/insights behind sparsity-based image denoising algorithms. In the first-generation (model-based) approaches, we will highlight the evolution from local wavelet-based image denoising in 1990s–2000s to nonlocal and patch-based image denoising from 2006 to 2015. In the second-generation (data-driven) approaches, we have opted to review several latest advances in the field of image denoising since 2016 such as learning parametric sparse models (for heavy noise removal) and deep learning -based approaches (including deep residue learning). The overarching theme of our review is to provide a unified conceptual understanding of why and how sparsity-based image denoising works—in particular, the evolving role played by models and data. Based on our critical review, we will discuss a few open issues and promising directions for future research.