Pré-Publication, Document De Travail Année : 2025

Multilevel Plug-and-Play Image Restoration

Résumé

Plug-and-play (PnP) image reconstruction methods leverage pretrained deep neural network denoisers as image priors to solve general inverse problems, and can obtain a competitive performance without having to train a network on a specific problem. Despite their flexibility, PnP methods often require several iterations to converge and their performance can be highly sensitive to the choice of the initialization and of the hyperparameters. In this paper, we propose a new multilevel PnP framework that accelerates the convergence by combining iterations at different scales, and improves the robustness to initialization and hyperparameters setting using a coarseto-fine strategy. In a series of experiments, including image inpainting and demosaicing, we show that the proposed multilevel PnP method outperforms other PnP methods in both speed and reconstruction performance.

Fichier principal
Vignette du fichier
A_Plug_and_Play_Approach_for_Multilevel_Image_Restoration_HAL.pdf (5.45 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05004914 , version 1 (25-03-2025)
hal-05004914 , version 2 (30-09-2025)
hal-05004914 , version 3 (30-04-2026)

Licence

Identifiants

  • HAL Id : hal-05004914 , version 1

Citer

Nils Laurent, Julián Tachella, Elisa Riccietti, Nelly Pustelnik. Multilevel Plug-and-Play Image Restoration. 2025. ⟨hal-05004914v1⟩
550 Consultations
952 Téléchargements

Partager

  • More