Wiener Guided DIP for Unsupervised Blind Image Deconvolution

TL;DR

This paper introduces a novel blind image deconvolution method guided by Wiener deconvolution, improving stability and performance by integrating frequency-based guidance into deep learning priors.

Contribution

It proposes a Wiener-guided approach that enhances unsupervised blind deconvolution by leveraging frequency domain information to stabilize and improve results.

Findings

Higher stability across multiple datasets

Faster reproduction of low-frequency features

Improved deconvolution performance

Abstract

Blind deconvolution is an ill-posed problem arising in various fields ranging from microscopy to astronomy. The ill-posed nature of the problem requires adequate priors to arrive to a desirable solution. Recently, it has been shown that deep learning architectures can serve as an image generation prior during unsupervised blind deconvolution optimization, however often exhibiting a performance fluctuation even on a single image. We propose to use Wiener-deconvolution to guide the image generator during optimization by providing it a sharpened version of the blurry image using an auxiliary kernel estimate starting from a Gaussian. We observe that the high-frequency artifacts of deconvolution are reproduced with a delay compared to low-frequency features. In addition, the image generator reproduces low-frequency features of the deconvolved image faster than that of a blurry image. We embed the computational process in a constrained optimization framework and show that the proposed method yields higher stability and performance across multiple datasets. In addition, we provide the code.