Variational methods for model comparison have become popular in the neural computing/machine learning literature. In this paper we explore their application to the Bayesian analys...
Variational methods are among the most accurate techniques for estimating the optic flow. They yield dense flow fields and can be designed such that they preserve discontinuities, ...
We present a novel variational method for estimating dense disparity maps from stereo images. It integrates the epipolar constraint into the currently most accurate optic flow met...
Abstract –In this paper, a variational message passing framework is proposed for Markov random fields, which is computationally more efficient and admits wider applicability comp...
We present a region-based active contour detection algorithm
for objects that exhibit relatively homogeneous photometric
characteristics (e.g. smooth color or gray levels),
embe...
Ganesh Sundaramoorthi, Stefano Soatto, Anthony Yez...
This paper focuses on matching 1D structures by variational methods. We provide rigorous rules for the construction of the cost function, on the basis of an analysis of properties ...