Measuring the Self-Consistency of Stereo Algorithms


Leclerc, Y. and Luong, Q.-T. and Fua, P. Measuring the self-consistency of stereo algorithms, in Proceedings of the European Conference on Computer Vision (ECCV2000), Dublin, Ireland, Jun 2000.


A new approach to characterizing the performance of point-correspondence algorithms is presented. Instead of relying on any “ground truth”, it uses the self-consistency of the outputs of an algorithm independently applied to different 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.

Read more from SRI