Blind image deblurring using class-adapted image priors

TL;DR

This paper introduces a class-adapted prior for blind image deblurring using Gaussian mixture models trained on specific image classes, improving restoration quality especially for text, faces, and fingerprints, even under high noise.

Contribution

It proposes a novel class-specific prior for BID using GMMs trained on particular image classes, enhancing deblurring performance over generic priors.

Findings

Outperforms state-of-the-art methods on class-specific images.

Effective at high noise levels for text images.

Achieves competitive restoration quality across different image classes.

Abstract

Blind image deblurring (BID) is an ill-posed inverse problem, usually addressed by imposing prior knowledge on the (unknown) image and on the blurring filter. Most of the work on BID has focused on natural images, using image priors based on statistical properties of generic natural images. However, in many applications, it is known that the image being recovered belongs to some specific class (e.g., text, face, fingerprints), and exploiting this knowledge allows obtaining more accurate priors. In this work, we propose a method where a Gaussian mixture model (GMM) is used to learn a class-adapted prior, by training on a dataset of clean images of that class. Experiments show the competitiveness of the proposed method in terms of restoration quality when dealing with images containing text, faces, or fingerprints. Additionally, experiments show that the proposed method is able to handle text images at high noise levels, outperforming state-of-the-art methods specifically designed for BID of text images.