We propose an algorithm that performs registration of large sets of unstructured point clouds of moving and deforming objects without computing correspondences. Given as input a s...
This paper presents a component based deformable
model for generalized face alignment, in which a novel bistage
statistical framework is proposed to account for both
local and g...
We present a new approach to iteratively estimate both
high-quality depth map and alpha matte from a single image
or a video sequence. Scene depth, which is invariant
to illumin...
Jiejie Zhu (University of Kentucky), Miao Liao (Un...
We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds i...
Non-linear dimensionality reductionmethods are powerful techniques to deal with
high-dimensional datasets. However, they often are susceptible to local minima
and perform poorly ...
Andreas Geiger (Karlsruhe Institute of Technology)...