Modeling Natural Images Using Gated MRFsEIWOS

摘要

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, with both mean and covariance determined by the configuration of latent variables, which is unlike previous models that were restricted to using Gaussians with either a fixed mean or a diagonal covar...更多
个人信息

 

您的评分 :

IEEE Trans. Pattern Anal. Mach. Intell., pp. 2206-2222, 2013.

被引用次数40|引用|30
标签
作者
评论