Abstract
Computer vision research rarely makes use of symmetry in stereo reconstruction despite its established importance in perceptual psychology. Such stereo reconstructions produce visually satisfying figures with precisely located points and lines, even when input images have low or moderate resolution. However, because few invariants exist, there are no known general approaches to solving symmetry correspondence on real images. The problem is significantly easier when combined with the binocular correspondence problem, because each correspondence problem provides strong non-overlapping constraints on the solution space. We demonstrate a system that leverages these constraints to produce accurate stereo models from pairs of binocular images using standard computer vision algorithms.
Keywords
symmetry correspondence binocular optimization shape
Session Number
03
Session Title
Binocular Vision and Stereo
Start Date
14-5-2015 11:05 AM
End Date
14-5-2015 11:30 AM
Recommended Citation
Michaux, Aaron and Pizlo, Zygmunt, "Two Correspondence Problems Easier Than One" (2015). MODVIS Workshop. 5.
https://docs.lib.purdue.edu/modvis/2015/session03/5
Included in
Artificial Intelligence and Robotics Commons, Cognition and Perception Commons, Other Computer Engineering Commons
Two Correspondence Problems Easier Than One
Computer vision research rarely makes use of symmetry in stereo reconstruction despite its established importance in perceptual psychology. Such stereo reconstructions produce visually satisfying figures with precisely located points and lines, even when input images have low or moderate resolution. However, because few invariants exist, there are no known general approaches to solving symmetry correspondence on real images. The problem is significantly easier when combined with the binocular correspondence problem, because each correspondence problem provides strong non-overlapping constraints on the solution space. We demonstrate a system that leverages these constraints to produce accurate stereo models from pairs of binocular images using standard computer vision algorithms.