Dictionary Learning for Deblurring and Digital Zoom

TL;DR

This paper introduces a dictionary learning approach for image deblurring and digital zooming, leveraging learned sparse local models trained on image pairs, achieving state-of-the-art results in these tasks.

Contribution

It presents a novel task-specific dictionary learning method using pairs of images, with an efficient stochastic gradient algorithm, improving deblurring and zooming performance.

Findings

Achieves state-of-the-art results on synthetic and real data.

Effective learning algorithm for task-specific dictionaries.

Convex optimization at test time ensures reliable image reconstruction.

Abstract

This paper proposes a novel approach to image deblurring and digital zooming using sparse local models of image appearance. These models, where small image patches are represented as linear combinations of a few elements drawn from some large set (dictionary) of candidates, have proven well adapted to several image restoration tasks. A key to their success has been to learn dictionaries adapted to the reconstruction of small image patches. In contrast, recent works have proposed instead to learn dictionaries which are not only adapted to data reconstruction, but also tuned for a specific task. We introduce here such an approach to deblurring and digital zoom, using pairs of blurry/sharp (or low-/high-resolution) images for training, as well as an effective stochastic gradient algorithm for solving the corresponding optimization task. Although this learning problem is not convex, once the dictionaries have been learned, the sharp/high-resolution image can be recovered via convex optimization at test time. Experiments with synthetic and real data demonstrate the effectiveness of the proposed approach, leading to state-of-the-art performance for non-blind image deblurring and digital zoom.