TL;DR
This paper presents an unrolled variational Bayesian algorithm integrated into a neural network for image blind deconvolution, improving visual quality and outperforming existing methods.
Contribution
It introduces a novel unrolled VBA framework within a neural network, enabling supervised training and hyperparameter optimization for image deblurring.
Findings
High performance on grayscale and color images
Outperforms state-of-the-art optimization and deep learning methods
Effective handling of diverse kernel shapes
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
