RENAUD, Marien; PROST, Jean; LECLAIRE, Arthur; PAPADAKIS, Nicolas

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

RENAUD, Marien
Institut de Mathématiques de Bordeaux [IMB]

PROST, Jean
Mathématiques Appliquées Paris 5 [MAP5 - UMR 8145]

LECLAIRE, Arthur
Image, Modélisation, Analyse, GEométrie, Synthèse [IMAGES]
Département Images, Données, Signal [IDS]

Langue

Document de travail - Pré-publication

Ce document a été publié dans

2024-02-01

Résumé en anglais

Plug-and-Play (PnP) algorithms are a class of iterative algorithms that address image inverse problems by combining a physical model and a deep neural network for regularization. Even if they produce impressive image restoration results, these algorithms rely on a non-standard use of a denoiser on images that are less and less noisy along the iterations, which contrasts with recent algorithms based on Diffusion Models (DM), where the denoiser is applied only on re-noised images. We propose a new PnP framework, called Stochastic deNOising REgularization (SNORE), which applies the denoiser only on images with noise of the adequate level. It is based on an explicit stochastic regularization, which leads to a stochastic gradient descent algorithm to solve ill-posed inverse problems. A convergence analysis of this algorithm and its annealing extension is provided. Experimentally, we prove that SNORE is competitive with respect to state-of-the-art methods on deblurring and inpainting tasks, both quantitatively and qualitatively.< Réduire

URI

https://oskar-bordeaux.fr/handle/20.500.12278/190243

Project ANR

Repenser la post-production d'archives avec des méthodes à patch, variationnelles et par apprentissage - ANR-19-CE23-0027

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251