Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution

• Published in: IEEE transactions on image processing Vol. 32; p. 1
• Main Authors: Huang, Yunshi, Chouzenoux, Emilie, Pesquet, Jean-Christophe
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; Bayes methods; Bayesian analysis; blind deconvolution; Color imagery; Deconvolution; Deep learning; Engineering Sciences; Image quality; Image restoration; Kernel; Kernels; Kullback-Leibler divergence; Machine learning; Majorization-Minimization; neural network; Neural networks; Optimization; Signal and Image processing; Smoothness; Training; Tuning; unrolling; Variational Bayesian approach; unrolling; deep learning; image restoration; Variational Bayesian approach; Majorization-Minimization; Kullback-Leibler divergence; neural network; blind deconvolution
• ISSN: 1057-7149; 1941-0042; 1941-0042
• DOI: 10.1109/TIP.2022.3224322

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 state-of-the-art techniques based on optimization, Bayesian estimation, or deep learning.