Fast Motion Deblurring


Sunghyun Cho

POSTECH

Seungyong Lee

POSTECH


ACM Transactions on Graphics (SIGGRAPH ASIA 2009), vol. 28, no. 5, article no. 145, December 2009

Deblur Famous Photo!

We have started a new project for fun! Check out its web page. It must be interesting for you!

News!

We are working with Adobe Systems in order to add deblurring feature to Photoshop. We cannot guarantee that Photoshop CS6 will be shipped with the deblurring feature though. Anyway, please enjoy the video below. The video shows a presentation given by Dr. Jue Wang at Adobe MAX 2011.


Abstract

This paper presents a fast deblurring method that produces a deblurring result from a single image of moderate size in a few seconds. We accelerate both latent image estimation and kernel estimation in an iterative deblurring process by introducing a novel prediction step and working with image derivatives rather than pixel values. In the prediction step, we use simple image processing techniques to predict strong edges from an estimated latent image, which will be solely used for kernel estimation. With this approach, a computationally efficient Gaussian prior becomes sufficient for deconvolution to estimate the latent image, as small deconvolution artifacts can be suppressed in the prediction. For kernel estimation, we formulate the optimization function using image derivatives, and accelerate the numerical process by reducing the number of Fourier transforms needed for a conjugate gradient method. We also show that the formulation results in a smaller condition number of the numerical system than the use of pixel values, which gives faster convergence. Experimental results demonstrate that our method runs an order of magnitude faster than previous work, while the deblurring quality is comparable. GPU implementation facilitates further speed-up, making our method fast enough for practical use.

Demo Video

This video was captured from the screen in real time. The actual speed of the program is higher than shown in the video as the screen capture software was consuming some computational resource when capturing the video. For more accurate measurements of the computation time, please see the tables in the paper. Please note that the quality of deblurred images has been degraded by video encoding.


Downloads

Executable

Please send e-mail to sodomau+deblur_cho2009__at__gmail.com, then we will send you the executable. Please note that the usage of the executable is permitted only for academic purpose. Please also describe who you are, and why you need the executable at least briefly when you send e-mail.

BibTex

@article {SCho_deblur_2009,
title = {Fast Motion Deblurring},
author = {Sunghyun Cho and Seungyong Lee},
journal = {ACM Transactions on Graphics (SIGGRAPH ASIA 2009)},
year = {2009},
volume = {28},
number = {5},
pages = {article no. 145}
}