Abstract

A half-occluded region in a stereo pair is a set of pixels in one image representing points in svace visible to that camera or eye only, and not to ihe other. These occur typically as parts of the background immediately to the left and right sides of nearby occluding objects, and are present in most natural scenes. Previous approaches to stereo either ignored these unmatchable points or attempted to weed them out in a second pass. Our algorithm incorporates them from the start as a strong clue to depth discontinuities. Psychophysical evidence suggests that the human visual system also exploits these clues. We start by deriving a measure for goodness of fit and a prior based on a simplified model of objects in space, which leads to an energy functional depending both on the depth as measured from a central “cyclopean ” eye and on the regions of points occluded from the left and right eye perspectives. We minimize this using dynamic programming along epipolar lines followed by annealing in both dimensions. Experiments indicate that this method is very effective even in difficult scenes. 1

Citations