DEEPBLUR: BLIND IDENTIFICATION OF SPACE VARIANT PSF - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

DEEPBLUR: BLIND IDENTIFICATION OF SPACE VARIANT PSF

Valentin Debarnot
Pierre Weiss

Résumé

We propose to train a neural network to estimate space varying blur operators from a single blurry image. The key assumption is that the operator lives in a subset of a known subspace, which is a reasonable assumption in many microscopes. We detail a specific sampling procedure of the subset to train a Resnet architecture. This allows a fast estimation. We finally illustrate the performance of the network on de-blurring problems. Index Terms-blur identification, neural network, non-uniform blur, blind debluring, blind inverse problem.
Fichier principal
Vignette du fichier
DeepBlur.pdf (498.19 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02998997 , version 1 (10-11-2020)

Identifiants

Citer

Valentin Debarnot, Pierre Weiss. DEEPBLUR: BLIND IDENTIFICATION OF SPACE VARIANT PSF. 2020. ⟨hal-02998997⟩
79 Consultations
376 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More