31 search results - page 2 / 7 » Convergent Tree-Reweighted Message Passing for Energy Minimi... |
ICIG
2009
IEEE
13 years 3 months ago
2009
IEEE
Optical flow estimation is one of the main subjects in computer vision. Many methods developed to compute the motion fields are built using standard heuristic formulation. In this...
JAIR
2011
12 years 8 months ago
2011
We address the problem of computing approximate marginals in Gaussian probabilistic models by using mean field and fractional Bethe approximations. We define the Gaussian fracti...
CVPR
2007
IEEE
14 years 7 months ago
2007
IEEE
We propose a novel MRF-based model for deformable image matching (also known as registration). The deformation is described by a field of discrete variables, representing displace...
ECCV
2008
Springer
14 years 3 months ago
2008
Springer
There are many local and greedy algorithms for energy minimization over Markov Random Field (MRF) such as iterated condition mode (ICM) and various gradient descent methods. Local ...
ECCV
2006
Springer
14 years 7 months ago
2006
Springer
Algorithms for discrete energy minimization play a fundamental role for low-level vision. Known techniques include graph cuts, belief propagation (BP) and recently introduced tree-...