Comparison of Optical Flow Methods under Stereomatching with Short Baselines
Tristan Dagobert, Nelson Monzón, Javier Sánchez
⚠ This is a preprint. It may change before it is accepted for publication.

Abstract

This article studies the effectiveness of optical flow methods employed in the case of short baselines and different noise levels. New metrics have been developed to analyze the evaluation results because the usual metrics are inadequate in a subpixel context. Experiments conducted on the adequate Middlebury and CMLA dataset pairs show that the Brox et al. method produces the best errors, with a 60% success rate in relative precision at 1/100 th of a pixel. On the other hand, our comparison shows that the Monzón et al. method also provides competitive results at the same time that it yields disparities with more details and correct contours.

Download

Non-Reviewed Supplementary Materials

These files and information are provided by the authors and have not been reviewed.