The Weizmann Institute of Science
Faculty of Mathematics and Computer Science
Vision and Robotics Seminar
Yair Weiss
School of Computer Science and Engineering
Hebrew University
will speak on
Learning to Perceive from Image Statistics -
a Computational Challenge
Abstract:
Natural images take up only a tiny fraction of the space of all possible
$N\times N$ matrices. It thus makes sense that perceptual systems, both
biological and artificial, would use image statistics to improve their
performance. This idea goes back at least to Mach (1886) and Helmholtz (1925)
operationalizing it for computer vision has proven to be difficult.
In this talk I will describe the computational challenges raised by such an
approach~- learning very non Gaussian distributions in high dimensional spaces
and performing inference with such distributions. I will then summarize some
of our research in this direction. The good news is that very simple
statistical models can lead to surprisingly powerful algorithms. The bad news
is that even these simple statistical models lead to complicated optimization
problems. Specifically, I will discuss applications of image statistics to
image denoising, ``inpainting" and transparency.
Joint work with A. Levin, A. Zomet and E. Levi.
The lecture will take place in the
Lecture Hall, Room 1, Ziskind Building
on Thursday, April 15, 2004
at noon