This paper develops and investigates a new approach for evaluating feature based object hypotheses in a direct way. The idea is to compute a feature likelihood map (FLM), which is ...
ACCV
In this paper we propose a novel approach to binocular stereo for fast matching of high-resolution images. Our approach builds a prior on the disparities by forming a ...
The conventional area-based stereo matching algorithm suffers from two problems, the windowing problem and computational cost. Multiple scale analysis has long been adopted in vis...
Abstract—In this paper, we propose a novel propagationbased stereo matching algorithm. Starting from an initial disparity map, our algorithm selects highly reliable pixels and pr...
A popular approach to pixel labeling problems, such as multiclass image segmentation, is to construct a pairwise conditional Markov random field (CRF) over image pixels where the...