Deep Gauss–Newton for phase retrieval - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Optics Letters Année : 2023

Deep Gauss–Newton for phase retrieval

Résumé

We propose the deep Gauss–Newton (DGN) algorithm. The DGN allows one to take into account the knowledge of the forward model in a deep neural network by unrolling a Gauss–Newton optimization method. No regularization or step size needs to be chosen; they are learned through convolutional neural networks. The proposed algorithm does not require an initial reconstruction and is able to retrieve simultaneously the phase and absorption from a single-distance diffraction pattern. The DGN method was applied to both simulated and experimental data and permitted large improvements of the reconstruction error and of the resolution compared with a state-of-the-art iterative method and another neural-network-based reconstruction algorithm.
Fichier principal
Vignette du fichier
Optics_Letters___DGNarticle.pdf (3.48 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04177989 , version 1 (07-08-2023)

Identifiants

Citer

Kannara Mom, Max Langer, Bruno Sixou. Deep Gauss–Newton for phase retrieval. Optics Letters, 2023, 48 (5), pp.1136. ⟨10.1364/OL.484862⟩. ⟨hal-04177989⟩
44 Consultations
52 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More