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.
|Original language||American English|
|Number of pages||14|
|Journal||IEEE Transactions on Pattern Analysis and Machine Intelligence|
|State||Published - 2011|
Bibliographical noteFunding Information:
The authors thank the Israel Science Foundation, US-Israel Bi-National Science Foundation, the Royal Dutch/Shell Group, NGA NEGI-1582-04-0004, MURI Grant N00014-06-1-0734, US National Science Foundation (NSF) CAREER award 0447561. F. Durand acknowledges a Microsoft Research New Faculty Fellowship and a Sloan Fellowship.
- Blind deconvolution
- motion deblurring
- natrual image statistics
- statistical estimation.