Pairwise comparison technique: a simple solution for depth reconstruction

Abstract

A new technique dramatically simplifies the analysis of matching and depth reconstruction by extracting three-dimensional rigid depth interpretation from pairwise comparisons of weak perspective projections. This method provides a simple linear criterion for testing the correctness of correspondence for a pair of images; the method also provides a description of a one-parameter family of interpretations for each pair of images that satisfies this criterion. We show that if at least three projections of a volumetric object are known, then a three-dimensional (3D) rigid interpretation can be inferred from pairwise comparisons between any one of these images and other images in the set. The 3D interpretation is derived from the intersection of corresponding one-parameter families. The method provides a common computational basis for different processes of depth perception, for example, depth-from-stereo and depth-from-motion. Thus, a single mechanism for these processes in the human visual system would be sufficient. The proposed method does not require information about relative positions of eye(s) or camera(s) for different projections, but this information can be easily incorporated. The method can be applied for pairwise comparison within a single image. If any nontrivial correspondence is found, then several views of the same object are present in the same image. This happens, for example, in views of volumetrically symmetric objects. Symmetry facilitates depth reconstruction; if an object possesses two or more symmetries, its depth can be reconstructed from a single image.