Abstract. Markov and Conditional random fields (CRFs) used in computer vision typically model only local interactions between variables, as this is computationally tractable. In t...
Abstract. We propose to tackle the optical flow problem by a combination of two recent advances in the computation of dense correspondences, namely the incorporation of image segme...
Michael Bleyer, Christoph Rhemann, Margrit Gelautz
An important research topic in image processing is stereo vision. The objective is to compute a 3-dimensional representation of some scenery from two 2-dimensional digital images....
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to...
We propose a method to identify and localize object
classes in images. Instead of operating at the pixel level,
we advocate the use of superpixels as the basic unit of a
class s...