Abstract
Stereo matching is an ill-posed problem for at least two prin- cipal reasons: (1) because of the random nature of match similarity mea- sure and (2) because of structural ambiguity due to repetitive patterns. Both ambiguities require the problem to be posed in the regularization framework. Continuity is a natural choice for a prior model. But this model may fail in low signal-to-noise ratio regions. The resulting arte- facts may then completely spoil the subsequent visual task. A question arises whether one could (1) find the unambiguous component of matching and, simultaneously, (2) identify the ambiguous component of the solution and then, optionally, (3) regularize the task for the am- biguous component only. Some authors have already taken this view. In this paper we define a new stability property which is a condition a set of matches must satisfy to be considered unambiguous at a given confi- dence level. It turns out that for a given matching problem this set is (1) unique and (2) it is already a matching. We give a fast algorithm that is able to find the largest stable matching. The algorithm is then used to show on real scenes that the unambiguous component is quite dense (10–80%) and error-free (total error rate of 0.3–1.4%), both depending on the con?dence level chosen.