Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Image Processing Year : 2022

Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution

Abstract

In this paper, we introduce a variational Bayesian algorithm (VBA) for image blind deconvolution. Our VBA generic framework incorporates smoothness priors on the unknown blur/image and possible affine constraints (e.g., sum to one) on the blur kernel, integrating the VBA within a neural network paradigm following an unrolling methodology. The proposed architecture is trained in a supervised fashion, which allows us to optimally set two key hyperparameters of the VBA model and leads to further improvements in terms of resulting visual quality. Various experiments involving grayscale/color images and diverse kernel shapes, are performed. The numerical examples illustrate the high performance of our approach when compared to stateof-the-art techniques based on optimization, Bayesian estimation, or deep learning.
Fichier principal
Vignette du fichier
main_tip.pdf (2.03 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03881393 , version 1 (01-12-2022)

Identifiers

Cite

Yunshi Huang, Emilie Chouzenoux, Jean-Christophe Pesquet. Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution. IEEE Transactions on Image Processing, 2022, 32, pp.430-445. ⟨10.1109/TIP.2022.3224322⟩. ⟨hal-03881393⟩
60 View
124 Download

Altmetric

Share

Gmail Facebook X LinkedIn More