A Deep Variational Bayesian Framework for Blind Image Deblurring

TL;DR

This paper introduces a deep variational Bayesian approach for blind image deblurring that jointly estimates the clean image and blur kernel, effectively integrating physical models with deep learning for improved results.

Contribution

It proposes a novel framework combining variational Bayesian inference with deep neural networks, considering the physical blur process and data priors for better deblurring performance.

Findings

Achieves promising deblurring results with simple networks

Enhances the performance of existing deep learning methods

Effectively models the physical degradation process

Abstract

Blind image deblurring is an important yet very challenging problem in low-level vision. Traditional optimization based methods generally formulate this task as a maximum-a-posteriori estimation or variational inference problem, whose performance highly relies on the handcraft priors for both the latent image and the blur kernel. In contrast, recent deep learning methods generally learn, from a large collection of training images, deep neural networks (DNNs) directly mapping the blurry image to the clean one or to the blur kernel, paying less attention to the physical degradation process of the blurry image. In this paper, we present a deep variational Bayesian framework for blind image deblurring. Under this framework, the posterior of the latent clean image and blur kernel can be jointly estimated in an amortized inference fashion with DNNs, and the involved inference DNNs can be trained by fully considering the physical blur model, together with the supervision of data driven priors for the clean image and blur kernel, which is naturally led to by the evidence lower bound objective. Comprehensive experiments are conducted to substantiate the effectiveness of the proposed framework. The results show that it can not only achieve a promising performance with relatively simple networks, but also enhance the performance of existing DNNs for deblurring.