Jump to Content
Your Recent History
View Cart
SUBSCRIPTIONS & PRICING
GENERAL INFORMATION
Logged Out Log In
Real-time image deconvolution on the GPU
Proc. SPIE 7872, 78720H (2011); http://dx.doi.org/10.1117/12.872152
Monday 24 January 2011
San Francisco Airport, California, USA
Parallel Processing for Imaging Applications
John D. Owens, I-Jong Lin, Yu-Jin Zhang, Giordano B. Beretta
Alerts
Alert Me When Cited
Alert Me When Corrected
Tools
Download Citation
Add to MyScitation
Blog This Article
Print-Friendly
Research Toolkit
Share
Email Abstract
Connotea
CiteULike
del.icio.us
BibSonomy
Tweet this Article
Add to FacebookTwo-dimensional image deconvolution is an important and well-studied problem with applications to image deblurring and restoration. Most of the best deconvolution algorithms use natural image statistics that act as priors to regularize the problem. Recently, Krishnan and Fergus provide a fast deconvolution algorithm that yields results comparable to the current state of the art. They use a hyper-Laplacian image prior to regularize the problem. The resulting optimization problem is solved using alternating minimization in conjunction with a half-quadratic penalty function. In this paper, we provide an efficient CUDA implementation of their algorithm on the GPU. Our implementation leverages many wellknown CUDA optimization techniques, as well as several others that have a significant impact on this particular algorithm. We discuss each of these, as well as make a few observations regarding the CUFFT library. Our experiments were run on an Nvidia GeForce GTX 260. For a single channel image of size 710 x 470, we obtain over 40 fps, while on a larger image of size 1900 x 1266, we get almost 6 fps (without counting disk I/O). In addition to linear performance, we believe ours is the first implementation to perform deconvolutions at video rates. Our running times also demonstrate that our GPU implementation is over 27 times faster than the original CPU implementation.
© 2010 COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.
History
Online Jan 25, 2011
Digital Object Identifier
Citation
James T. Klosowski and Shankar Krishnan, "Real-time image deconvolution on the GPU",
Proc. SPIE 7872, 78720H (2011); http://dx.doi.org/10.1117/12.872152
DOWNLOAD ARTICLE
RELATED CONTENT
More Like This Article
For access to fully linked references, you need to log in.
SPIE Digital Library
This Publication
Google Scholar
PubMed