@device(postscript)
@libraryfile(Mathematics10)
@libraryfile(Accents)
@style(fontfamily=timesroman,fontscale=11)
@pagefooting(immediate, left "@c<Technical Report 1996>",
center "@c<Computer Science>",
right "@c<Carnegie Mellon>")
@heading(Multi-baseline Stereo Using Surface Extraction)
@heading(CMU-CS-96-196)
@center(@b(C. Lawrence Zitnick, Jon A. Webb))
@center(November 1996)
@center(FTP: CMU-CS-96-196.ps)
@blankspace(1)
@begin(text)

Traditionally, the matching problem in stereo vision has been 
formulated as an ill-posed problem.  However, it has been shown that
the matching problem can be well-posed in scenes with no occlusions
or depth discontinuities.  Unfortunately most real scenes do not obey
these constraints.  We overcome this by finding regions within the
images in which the matching problem is well-posed.  That is, we find
image regions in which there are no occlusions or depth discontinuities.
In general, a unique set of such regions does not exist.  However, we 
will demonstrate that in almost all cases these regions can be found
efficiently.  Therefore the matching problem can be well-posed in
almost all cases.

In order to find these corresponding regions we transform the problem
from finding 2D image regions into identifying 3D surfaces.  We have
developed a method of 3D surface extraction which uniquely identifies 
correct 3D surfaces from a set of potential surfaces.  In order to
test the method we have built a four camera system with which we will
present results from several scenes.

@blankspace(2line)
@begin(transparent,size=10)
@b(Keywords:@ )@c<Early vision, stereo vision, multi-baseline, well-posed
problems>
@end(transparent)
@blankspace(1line)
@end(text)
@flushright(@b[(30 pages)])