Blind Image Deblurring via Reweighted Graph Total Variation

TL;DR

This paper introduces a novel reweighted graph total variation prior for blind image deblurring, enabling accurate kernel estimation and high-quality image restoration through an efficient alternating optimization algorithm.

Contribution

It proposes a new RGTV prior based on skeleton images for better kernel estimation in blind deblurring, with a fast algorithm for non-convex optimization.

Findings

Robust kernel estimation with large kernels

Competitive sharp image reconstruction

Effective handling of ill-posed deblurring problem

Abstract

Blind image deblurring, i.e., deblurring without knowledge of the blur kernel, is a highly ill-posed problem. The problem can be solved in two parts: i) estimate a blur kernel from the blurry image, and ii) given estimated blur kernel, de-convolve blurry input to restore the target image. In this paper, by interpreting an image patch as a signal on a weighted graph, we first argue that a skeleton image---a proxy that retains the strong gradients of the target but smooths out the details---can be used to accurately estimate the blur kernel and has a unique bi-modal edge weight distribution. We then design a reweighted graph total variation (RGTV) prior that can efficiently promote bi-modal edge weight distribution given a blurry patch. However, minimizing a blind image deblurring objective with RGTV results in a non-convex non-differentiable optimization problem. We propose a fast algorithm that solves for the skeleton image and the blur kernel alternately. Finally with the computed blur kernel, recent non-blind image deblurring algorithms can be applied to restore the target image. Experimental results show that our algorithm can robustly estimate the blur kernel with large kernel size, and the reconstructed sharp image is competitive against the state-of-the-art methods.