DIVA: Deep Unfolded Network from Quantum Interactive Patches for Image Restoration - Laboratoire de Physique Théorique - LPT Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

DIVA: Deep Unfolded Network from Quantum Interactive Patches for Image Restoration

Résumé

This paper presents a deep neural network called DIVA unfolding a baseline adaptive denoising algorithm (De-QuIP), relying on the theory of quantum many-body physics. Furthermore, it is shown that with very slight modifications, this network can be enhanced to solve more challenging image restoration tasks such as image deblurring, super-resolution and inpainting. Despite a compact and interpretable (from a physical perspective) architecture, the proposed deep learning network outperforms several recent algorithms from the literature, designed specifically for each task. The key ingredients of the proposed method are on one hand, its ability to handle non-local image structures through the patch-interaction term and the quantum-based Hamiltonian operator, and, on the other hand, its flexibility to adapt the hyperparameters patch-wisely, due to the training process.
Fichier principal
Vignette du fichier
2301.00247.pdf (7.32 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
licence : CC BY - Paternité

Dates et versions

hal-03920461 , version 1 (03-01-2023)

Identifiants

Citer

Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, Denis Kouamé. DIVA: Deep Unfolded Network from Quantum Interactive Patches for Image Restoration. 2023. ⟨hal-03920461⟩
113 Consultations
22 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More