Explicit Diffusion of Gaussian Mixture Model Based Image Priors

Martin Zach, Thomas Pock, Erich Kobler, Antonin Chambolle

Abstract: In this work we tackle the problem of estimating the density $$ f_X $$ of a random variable $$ X $$ by successive smoothing, such that the smoothed random variable $$ Y $$ fulfills $$ (\partial _t - \varDelta _1)f_Y(\,\cdot \,, t) = 0 $$ , $$ f_Y(\,\cdot \,, 0) = f_X $$ . With a focus on image processing, we propose a product/fields-of-experts model with Gaussian mixture experts that admits an analytic expression for $$f_Y (\,\cdot \,, t)$$ under an orthogonality constraint on the filters. This construction naturally allows the model to be trained simultaneously over the entire diffusion horizon using empirical Bayes. We show preliminary results on image denoising where our model leads to competitive results while being tractable, interpretable, and having only a small number of learnable parameters. As a byproduct, our model can be used for reliable noise estimation, allowing blind denoising of images corrupted by heteroscedastic noise.