Accurate estimation of optical flow is a challenging task, which often requires addressing difficult energy optimization problems. To solve them, most top-performing methods rely ...
A mechanism for efficient mean-shift belief propagation (MSBP) is introduced. The novelty of our work is to use mean-shift to perform nonparametric mode-seeking on belief surfaces...
Abstract. Statistical learning techniques have been used to dramatically speed-up keypoint matching by training a classifier to recognize a specific set of keypoints. However, the ...
Abstract. Traditional stereo algorithms implicitly use the frontal parallel plane assumption when exploiting contextual information, since the smoothness prior biases towards const...
Piecewise constant and piecewise smooth Mumford-Shah (MS) models have been widely studied and used for image segmentation. More complicated than piecewise constant MS, global Gaus...