Direct Sparse Deblurring

Speaker:	Professor Stefano Soatto, Vision Lab, UCLA

Title: 		"Direct Sparse Deblurring"

Date:		Thursday, 26 March 2009

Time:		4:00pm - 5:00pm

Venue:		Room 3412 (via lifts 17/18), HKUST


Abstract:

We propose a deblurring algorithm that explicitly takes into account the
sparse characteristics of natural images and that does not entail solving
a numerically ill-conditioned backward-diffusion. The key observation is
that the sparse coefficients that encode a given image with respect to an
over-complete basis are the same that encode a blurred version of the
image with respect to a modified basis. Following an
``analysis-by-synthesis'' approach, an explicit generative model is used
to compute a sparse representation of the blurred image, and then the
coefficients used to combine elements of the original basis to yield a
restored image. We compare our algorithm against the state of the art in
variational methods as well as wavelet- based algorithms.

**********************
Biography:

Please visit http://www.cs.ucla.edu/~soatto/ for details.