Blind Image Deblurring with FFT-ReLU Sparsity Prior

TL;DR

This paper presents a novel blind image deblurring method using an FFT-ReLU sparsity prior, achieving competitive results with faster inference, suitable for various image types.

Contribution

It introduces a new FFT-ReLU sparsity prior for blind deblurring, improving efficiency and effectiveness over existing methods.

Findings

Achieves results comparable to state-of-the-art algorithms.

Offers up to two times faster inference.

Effective across diverse image types.

Abstract

Blind image deblurring is the process of recovering a sharp image from a blurred one without prior knowledge about the blur kernel. It is a small data problem, since the key challenge lies in estimating the unknown degrees of blur from a single image or limited data, instead of learning from large datasets. The solution depends heavily on developing algorithms that effectively model the image degradation process. We introduce a method that leverages a prior which targets the blur kernel to achieve effective deblurring across a wide range of image types. In our extensive empirical analysis, our algorithm achieves results that are competitive with the state-of-the-art blind image deblurring algorithms, and it offers up to two times faster inference, making it a highly efficient solution.