Understanding Blind Deconvolution Algorithms

TLDR

Blind deconvolution seeks to recover a sharp image from a blurred observation with an unknown kernel, a problem that has seen recent progress but remains challenging, making experimental evaluation on ground‑truth data essential. The goal of this paper is to analyze and evaluate recent blind deconvolution algorithms both theoretically and experimentally. As a first step toward this experimental evaluation, we collected ground‑truth blur data and compared recent algorithms under equal settings. We show that the naive MAP approach fails because it favors no‑blur explanations, that joint MAP estimation of image and kernel also fails even with large images, but that MAP estimation of the kernel alone succeeds when the kernel is smaller than the image, and our data reveal that the shift‑invariant blur assumption is frequently violated.

Abstract

Blind deconvolution is the recovery of a sharp version of a blurred image when the blur kernel is unknown. Recent algorithms have afforded dramatic progress, yet many aspects of the problem remain challenging and hard to understand. The goal of this paper is to analyze and evaluate recent blind deconvolution algorithms both theoretically and experimentally. We explain the previously reported failure of the naive MAP approach by demonstrating that it mostly favors no-blur explanations. We show that, using reasonable image priors, a naive simulations MAP estimation of both latent image and blur kernel is guaranteed to fail even with infinitely large images sampled from the prior. On the other hand, we show that since the kernel size is often smaller than the image size, a MAP estimation of the kernel alone is well constrained and is guaranteed to succeed to recover the true blur. The plethora of recent deconvolution techniques makes an experimental evaluation on ground-truth data important. As a first step toward this experimental evaluation, we have collected blur data with ground truth and compared recent algorithms under equal settings. Additionally, our data demonstrate that the shift-invariant blur assumption made by most algorithms is often violated.