Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution
Huang, Yunshi, Chouzenoux, Emilie, Pesquet, Jean-Christophe
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Oct-14-2021
- Country:
- North America
- United States
- Colorado (0.04)
- Washington > King County
- Seattle (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Florida > Miami-Dade County
- Miami (0.04)
- Alaska > Anchorage Municipality
- Anchorage (0.04)
- Canada
- United States
- Europe
- France (0.04)
- United Kingdom > England
- East Sussex > Brighton (0.04)
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- Denmark > North Jutland
- Aalborg (0.04)
- Asia
- China (0.04)
- South Korea > Daejeon
- Daejeon (0.04)
- North America
- Genre:
- Research Report > Promising Solution (0.48)
- Industry:
- Health & Medicine > Diagnostic Medicine > Imaging (0.67)
- Technology: