Daniel Zoran (Hebrew University of Jerusalem)
Tuesday, 18.6.2013, 11:30
Simple Gaussian Mixture Models (GMMs) learned from pixels of natural image
patches have been recently shown to be surprisingly strong performers in
modeling the statistics of natural images. Here we provide an in depth
analysis of this simple yet rich model. We show that such a GMM model is
able to compete with even the most successful models of natural images in
log likelihood scores, denoising performance and sample quality. We provide
an analysis of what such a model learns from natural images as a function of
number of mixture components --- including covariance structure, contrast
variation and intricate structures such as textures, boundaries and more.
Finally, we show that the salient properties of the GMM learned from natural
images can be derived from a simplified Dead Leaves model which explicitly
models occlusion, explaining its surprising success relative to other models.