What makes a good model of natural images?

Many low-level vision algorithms assume a prior probability over images, and there has been great interest in trying to learn this prior from examples. Since images are very non Gaussian, high dimensional, continuous signals, learning their distribution presents a tremendous computational challenge. Perhaps the most successful recent algorithm is the Fields of Experts (FOE) [20] model which has shown impressive performance by modeling image statistics with a product of potentials defined on filter outputs. However, as in previous models of images based on filter outputs [30], calculating the probability of an image given the model requires evaluating an intractable partition function. This makes learning very slow (requires Monte-Carlo sampling at every step) and makes it virtually impossible to compare the likelihood of two different models. Given this computational difficulty, it is hard to say whether nonintuitive features learned by such models represent a true property of natural...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Yair Weiss, William T. Freeman
• Keywords: Computer Vision, CVPR 2007, Efficient Learning Algorithms, Filter Outputs, Gaussian Potentials, Intractable Partition Function, Maximum Likelihood Filters