Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution
This work addresses image restoration for applications like photography or medical imaging, but it is incremental as it combines existing techniques (VBA and unrolling) in a novel way.
The paper tackles image blind deconvolution by introducing a variational Bayesian algorithm integrated into a neural network via unrolling, achieving high performance compared to state-of-the-art methods in experiments with grayscale/color images and diverse kernels.
In this paper, we introduce a variational Bayesian algorithm (VBA) for image blind deconvolution. Our generic framework incorporates smoothness priors on the unknown blur/image and possible affine constraints (e.g., sum to one) on the blur kernel. One of our main contributions is the integration of 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 lead 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.