Characterizing the Performance of Multiple-Image Point-Correspondence Algorithms Using Self-Consistency

A new approach to characterizing the performance of point-correspondencealgorithmsis presented. Instead of relyingon any \ground truth', it uses the self-consistency of the outputs of an algorithm independently applied to di erent sets of views of a static scene. It allows one to evaluate algorithms for a given class of scenes, as well as to estimate the accuracy of every element of the output of the algorithm for a given set of views. Experiments to demonstrate the usefulness of the methodology are presented.

• Type: Conference
• Year: 1999
• Where: ICCVW
• Authors: Yvan G. Leclerc, Quang-Tuan Luong, Pascal Fua
• Keywords: Algorithm, Computer Vision, Erent Sets, ICCVW 1999, \ground Truth