The Production of Ground Truths for Evaluating Highly Accurate Stereovision Algorithms
Tristan Dagobert
⚠ This is a preprint. It may change before it is accepted for publication.


The construction and improvement of algorithms for subpixel stereovision requires very precise test databases. The state of the art on the sets of images used extensively by the scientific community shows that they are often incomplete and imprecise compared to the set objectives. We will present a method based on image synthesis to produce stereoscopic pairs to which are associated ground truths such as disparity and occlusion maps reaching an accuracy of about 1e-6. The a priori noise estimate is also taken into account. This process allows us to deliver a new image database consisting of 66 stereo pairs together with their ground truths.


Supplementary Materials

Available datasets (described in the manuscript):