Filling-in some of the decoding gap between belief propagation (BP) and maximum a posteriori (MAP) for convolutional codes.
Peter C. MasseyPublished in: ISIT (2004)
Keyphrases
- belief propagation
- maximum a posteriori
- markov random field
- energy function
- map estimation
- message passing
- graph cuts
- bayesian framework
- markov networks
- loopy belief propagation
- higher order
- image segmentation
- prior model
- image restoration
- approximate inference
- hyperparameters
- graphical models
- pairwise
- posterior distribution
- parameter estimation
- conditional random fields
- generalized gaussian
- free energy
- prior distribution
- stereo matching
- maximum likelihood
- image reconstruction
- max product
- variable length
- computer vision
- em algorithm
- probabilistic model
- multiresolution
- high quality