Mixtures of Conditional Gaussian Scale Mixtures Applied to Multiscale Image Representations

We present a probabilistic model for natural images that is based on mixtures of Gaussian scale mixtures and a simple multiscale representation. We show that it is able to generate images with interesting higher-order correlations when trained on natural images or samples from an occlusion-based model. More importantly, our multiscale model allows for a principled evaluation. While it is easy to generate visually appealing images, we demonstrate that our model also yields the best performance reported to date when evaluated with respect to the cross-entropy rate, a measure tightly linked to the average log-likelihood. The ability to quantitatively evaluate our model differentiates it from other multiscale models, for which evaluation of these kinds of measures is usually intractable.

[1]  Albert Perez Ε-admissible Simplifications of the Dependence Structure of a Set of Random Variables , 1977, Kybernetika.

[2]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[3]  Thomas M. Cover,et al.  Elements of Information Theory , 1991 .

[4]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[5]  Arjun K. Gupta,et al.  Lp-norm spherical distribution , 1997 .

[6]  J. V. van Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[7]  J. H. Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998 .

[8]  Martin J. Wainwright,et al.  Scale Mixtures of Gaussians and the Statistics of Natural Images , 1999, NIPS.

[9]  Ann B. Lee An Occlusion Model Generating Scale-Invariant Images , 1999 .

[10]  D K Smith Numerical Optimization , 2001, J. Oper. Res. Soc..

[11]  Eero P. Simoncelli,et al.  Natural image statistics and neural representation. , 2001, Annual review of neuroscience.

[12]  David Mumford,et al.  Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves Model , 2004, International Journal of Computer Vision.

[13]  Song-Chun Zhu,et al.  From Information Scaling of Natural Images to Regimes of Statistical Models , 2007 .

[14]  Eero P. Simoncelli,et al.  Statistical Modeling of Images with Fields of Gaussian Scale Mixtures , 2006, NIPS.

[15]  Thomas M. Cover,et al.  Elements of information theory (2. ed.) , 2006 .

[16]  William T. Freeman,et al.  What makes a good model of natural images? , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Eero P. Simoncelli,et al.  Image denoising using mixtures of Gaussian scale mixtures , 2008, 2008 15th IEEE International Conference on Image Processing.

[18]  Yiannis Aloimonos,et al.  Who killed the directed model? , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  J. Gallant,et al.  1.17 – Neural Mechanisms of Natural Scene Perception , 2008 .

[20]  Matthias Bethge,et al.  Hierarchical Modeling of Local Image Features through $L_p$-Nested Symmetric Distributions , 2009, NIPS.

[21]  卢耕博,et al.  Bit rate control method and device for image compression , 2010 .

[22]  Geoffrey E. Hinton,et al.  Generating more realistic images using gated MRF's , 2010, NIPS.

[23]  Matthias Bethge,et al.  Lower bounds on the redundancy of natural images , 2010, Vision Research.