Abstract. We study an energy functional for computing optical flow that combines three assumptions: a brightness constancy assumption, a gradient constancy assumption, and a discon...
Abstract. There has been much effort invested in increasing the robustness of human body tracking by incorporating motion models. Most approaches are probabilistic in nature and se...
Mean shift is a nonparametric estimator of density which has been applied to image and video segmentation. Traditional mean shift based segmentation uses a radially symmetric kerne...
Jue Wang, Bo Thiesson, Yingqing Xu, Michael F. Coh...
This paper presents a practical method for finding the provably globally optimal solution to numerous problems in projective geometry including multiview triangulation, camera rese...
Abstract. We formulate a robust method using Expectation Maximization (EM) to address the problem of dense photometric stereo. Previous approaches using Markov Random Fields (MRF) ...