A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors.
Richard SzeliskiRamin ZabihDaniel ScharsteinOlga VekslerVladimir KolmogorovAseem AgarwalaMarshall F. TappenCarsten RotherPublished in: IEEE Trans. Pattern Anal. Mach. Intell. (2008)
Keyphrases
- energy minimization
- markov random field
- energy function
- graph cuts
- problems in computer vision
- belief propagation
- image segmentation
- low level vision
- maximum a posteriori
- higher order
- loopy belief propagation
- iterated conditional modes
- conditional random fields
- image restoration
- dual decomposition
- labeling problems
- mrf models
- max flow min cut
- higher order cliques
- random fields
- pairwise
- early vision
- image prior
- interactive segmentation
- max flow
- mrf model
- machine learning
- message passing
- expectation maximization
- simulated annealing
- energy minimization problems
- computer vision