Denoising: from classical methods to deep CNNs - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Denoising: from classical methods to deep CNNs

Résumé

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.

Dates et versions

hal-04560694 , version 1 (26-04-2024)

Identifiants

Citer

Jean-Eric Campagne. Denoising: from classical methods to deep CNNs. 2024. ⟨hal-04560694⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More