The Weizmann Institute of Science
Faculty of Mathematics and Computer Science
Vision and Robotics Seminar
School of Computer Science \& Engineering
will speak on
Learning to perceive transparency
from the statistics of natural scenes
Certain simple images are known to trigger a percept of transparency: the input
image $I$ is perceived as the sum of two images $I(x;y)=I1(x;y)+I2(x;y)$. This
percept is puzzling. First, why do we choose the ``more complicated"
description with two images rather than the ``simpler" explanation
$I(x;y)=I1(x;y)+0$? Second, given the infnite number of ways to express $I$ as
a sum of two images, how do we compute the ``best" decomposition? Here we
suggest that transparency is the rational percept of a system that is adapted
to the statistics of natural scenes. We present a probabilistic model of
images based on the qualitative statistics of derivative filters and corner
``detectors" in natural scenes, that use this model to find the most probable
decomposition of a novel image. The optimization is performed using loopy
belief propagation. We show that our model computes perceptually ``correct"
decompositions on real and synthetic images.
This is joint work with Assaf Zomet and Yair Weiss.
The lecture will take place in the
Lecture Hall, Room 1, Ziskind Building
on Thursday, November 21, 2002