Mixtures of conditional Gaussian scale mixtures applied to multiscale image representations

Abstract

We present a probabilistic model for natural images which is based on Gaussian scale mixtures and a simple multiscale representation. In contrast to the dominant approach to modeling whole images focusing on Markov random fields, we formulate our model in terms of a directed graphical model. 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, the directed model enables us to perform 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.

Cited by in corpus (11)

• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• Video (language) modeling: a baseline for generative models of natural videos
• Generative Image Modeling Using Spatial LSTMs
• RNADE: The real-valued neural autoregressive density-estimator
• PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
• CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
• Photo-Realistic Video Prediction on Natural Videos of Largely Changing Frames
• Learning to Generate Chairs, Tables and Cars with Convolutional Networks
• Diverse feature visualizations reveal invariances in early layers of deep neural networks
• A Generative Model of Natural Texture Surrogates
• Probabilistic Model of Visual Segmentation