Photon-Limited Blind Deconvolution using Unsupervised Iterative Kernel Estimation

TL;DR

This paper introduces an unsupervised iterative kernel estimation method for blind deconvolution in low-light conditions, effectively handling photon shot noise and outperforming existing algorithms.

Contribution

It reformulates blind deconvolution into a kernel-based minimization and integrates an iterative scheme with a pre-trained non-blind solver for improved low-light deblurring.

Findings

Outperforms state-of-the-art algorithms in low-light deconvolution

Effective handling of photon shot noise in blind deconvolution

Demonstrates robustness of the iterative kernel estimation approach

Abstract

Blind deconvolution is a challenging problem, but in low-light it is even more difficult. Existing algorithms, both classical and deep-learning based, are not designed for this condition. When the photon shot noise is strong, conventional deconvolution methods fail because (1) the image does not have enough signal-to-noise ratio to perform the blur estimation; (2) While deep neural networks are powerful, many of them do not consider the forward process. When the noise is strong, these networks fail to simultaneously deblur and denoise; (3) While iterative schemes are known to be robust in the classical frameworks, they are seldom considered in deep neural networks because it requires a differentiable non-blind solver. This paper addresses the above challenges by presenting an \emph{unsupervised} blind deconvolution method. At the core of this method is a reformulation of the general blind deconvolution framework from the conventional image-kernel alternating minimization to a purely kernel-based minimization. This kernel-based minimization leads to a new iterative scheme that backpropagates an unsupervised loss through a pre-trained non-blind solver to update the blur kernel. Experimental results show that the proposed framework achieves superior results than state-of-the-art blind deconvolution algorithms in low-light conditions.