Modeling Natural Images Using Gated MRFs
Pattern Analysis and Machine Intelligence, IEEE Transactions, Volume 35, Issue 9, 2013, Pages 2206-2222.
Gaussian processesMarkov processesbelief networksimage processingGaussian processMore(22+)
This paper describes a Markov Random Field for real-valued image modeling that has two sets of latent variables. One set is used to gate the interactions between all pairs of pixels, while the second set determines the mean intensities of each pixel. This is a powerful model with a conditional distribution over the input that is Gaussian,...More
Full Text (Upload PDF)
PPT (Upload PPT)