Denoising: from classical methods to deep CNNs
It provides a pedagogical overview of denoising methods, which is incremental as it synthesizes existing knowledge without introducing new techniques.
This paper reviews the evolution of image denoising from classical methods like Fourier analysis to deep CNNs such as U-Net, highlighting their adaptability to various image types and optimal results, with denoising playing a key role in probability density estimation for image generation.
This paper aims to explore the evolution of image denoising in a pedagological way. We briefly review classical methods such as Fourier analysis and wavelet bases, highlighting the challenges they faced until the emergence of neural networks, notably the U-Net, in the 2010s. The remarkable performance of these networks has been demonstrated in studies such as Kadkhodaie et al. (2024). They exhibit adaptability to various image types, including those with fixed regularity, facial images, and bedroom scenes, achieving optimal results and biased towards geometry-adaptive harmonic basis. The introduction of score diffusion has played a crucial role in image generation. In this context, denoising becomes essential as it facilitates the estimation of probability density scores. We discuss the prerequisites for genuine learning of probability densities, offering insights that extend from mathematical research to the implications of universal structures.