27 February 2015 Blind deconvolution of images with model discrepancies using maximum a posteriori estimation with heavy-tailed priors
Author Affiliations +
Abstract
Single image blind deconvolution aims to estimate the unknown blur from a single observed blurred image and recover the original sharp image. Such task is severely ill-posed and typical approaches involve some heuristic or other steps without clear mathematical explanation to arrive at an acceptable solution. We show that a straight- forward maximum a posteriori estimation incorporating sparse priors and mechanism to deal with boundary artifacts, combined with an efficient numerical method can produce results which compete with or outperform much more complicated state-of-the-art methods. Our method is naturally extended to deal with overexposure in low-light photography, where linear blurring model is violated.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jan Kotera, Jan Kotera, Filip Šroubek, Filip Šroubek, "Blind deconvolution of images with model discrepancies using maximum a posteriori estimation with heavy-tailed priors", Proc. SPIE 9404, Digital Photography XI, 94040B (27 February 2015); doi: 10.1117/12.2077158; https://doi.org/10.1117/12.2077158
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Deconvolution with a spatially variant PSF
Proceedings of SPIE (December 18 2002)
Generalized Back-Projection Method
Proceedings of SPIE (October 13 1987)
Blind deconvolution of images using neural networks
Proceedings of SPIE (July 07 1994)

Back to Top