Fields of Experts: High-order Markov Random Field Models of Natural Scenes

Joint Seminar
                             =============
Department of Computer Science and Engineering
Department of Electronic and Computer Engineering
------------------------------------------------------------------------
Speaker:	Professor Michael J. Black
		Department of Computer Science
		Brown University

Title:		"Fields of Experts: High-order Markov Random Field
		 Models of Natural Scenes"

Date:		Thursday, 23 August 2007

Time:		3:00pm - 4:00pm

Venue:		Lecture Theatre F
		(Leung Yat Sing Lecture Theatre, near lift nos. 25/26)
		HKUST

Abstract:

We develop a framework for learning generic, expressive image priors that
capture the statistics of natural scenes and can be used for Bayesian
inference in a variety of machine vision tasks. The approach provides a
practical method for learning high-order Markov Random Field (MRF) models
with potential functions that extend over large pixel neighborhoods. These
high-order models significantly increase the expressive power of MRFs. The
key insight involves modeling the MRF potentials using a
Products-of-Experts framework that exploits non-linear functions of many
linear filter responses. In contrast to previous MRF approaches all
parameters, including the linear filters themselves, are learned from
training data. We demonstrate the capabilities of this Field of Experts
(FoE) model with two example applications in archival film restoration:
image denoising and image inpainting. Film grain noise in archival films
is particularly challenging because it varies with image intensity, is
non-Gaussian, and is spatially correlated. While the FoE model is trained
on a generic image database, and is not tuned toward a specific
application, we obtain results that compete with and even outperform
specialized techniques. If time permits, applications of the FoE model to
optical flow estimation will be briefly mentioned.

This is joint work with Stefan Roth and Teodor Moldovan.


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

Michael Black received his B.Sc. from the University of British Columbia
(1985), his M.S. from Stanford (1989), and his Ph.D. in computer science
from Yale University in 1992.  He has been a visiting researcher at the
NASA Ames Research Center and an Assistant professor in the Dept. of
Computer Science at the University of Toronto.  In 1993 Prof. Black joined
the Xerox Palo Alto Research Center where he managed the Image
Understanding area and later founded the Digital Video Analysis group.  In
2000, Prof. Black joined the faculty of Brown University where he is a
Professor of Computer Science.  At CVPR'91 he received the IEEE Computer
Society Outstanding Paper Award for his work with P. Anandan on robust
optical flow estimation.  His work also received Honorable Mention for the
Marr Prize in 1999 (with David Fleet) and 2005 (with Stefan Roth). Prof.
Black's research interests in machine vision include optical flow
estimation, human motion analysis and probabilistic models of the visual
world.  In computational neuroscience his work focuses on probabilistic
models of the neural code, the neural control of movement and the
development of neural prostheses that directly connect brains and machines
to restore lost function to the physically disabled.