Unsupervised linear and Iterative combinations of patches for image denoising - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Unsupervised linear and Iterative combinations of patches for image denoising

Résumé

We introduce a parametric view of non-local two-step denoisers, for which BM3D is a major representative, where quadratic risk minimization is leveraged for unsupervised optimization. Within this paradigm, we propose to extend the underlying mathematical parametric formulation by iteration. This generalization can be expected to further improve the denoising performance, somehow curbed by the impracticality of repeating the second stage for all two-step denoisers. The resulting formulation involves estimating an even larger amount of parameters in a unsupervised manner which is all the more challenging. Focusing on the parameterized form of NL-Ridge, the simplest but also most efficient non-local two-step denoiser, we propose a progressive scheme to approximate the parameters minimizing the risk. In the end, the denoised images are made up of iterative linear combinations of patches. Experiments on artificially noisy images but also on real-world noisy images demonstrate that our method compares favorably with the very best unsupervised denoisers such as WNNM, outperforming the recent deep-learning-based approaches, while being much faster.
Fichier principal
Vignette du fichier
LIChI.pdf (5.67 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03894346 , version 1 (12-12-2022)

Identifiants

  • HAL Id : hal-03894346 , version 1

Citer

Sébastien Herbreteau, Charles Kervrann. Unsupervised linear and Iterative combinations of patches for image denoising. 2022. ⟨hal-03894346⟩
24 Consultations
7 Téléchargements

Partager

Gmail Facebook X LinkedIn More