Abstract
We develop a sequential optimal sampling frameworkfor stereo disparity estimation by adapting the SequentialProbability Ratio Test (SPRT) model. We operate over localimage neighborhoods by iteratively estimating single pixeldisparity values until sufficient evidence has been gatheredto either validate or contradict the current hypothesis re-garding local scene structure. The output of our sampling is a set of sampled pixel positions along with a robust and compact estimate of the set of disparities contained within a given region. We further propose an efficient plane propagation mechanism that leverages the pre-computed sampling positions and the local structure model described bythe reduced local disparity set. Our sampling frameworkis a general pre-processing mechanism aimed at reducing computational complexity of disparity search algorithms by ascertaining a reduced set of disparity hypotheses for each pixel. Experiments demonstrate the effectiveness of the proposed approach when compared to state of the art methods.