Abstract

Belief propagation (BP) has become widely used for low-level vision problems and various inference techniques have been proposed for loopy graphs. These methods typically rely on ad hoc spatial priors such as the Potts model. In this paper we investigate the use of learned mod- els of image structure, and demonstrate the improvements obtained over previous ad hoc models for the image denoising problem. In particu- lar, we show how both pairwise and higher-order Markov random fields with learned clique potentials capture rich image structures that bet- ter represent the properties of natural images. These models are learned using the recently proposed Fields-of-Experts framework. For such mod- els, however, traditional BP is computationally expensive. Consequently we propose some approximation methods that make BP with learned potentials practical. In the case of pairwise models we propose a novel approximation of robust potentials using a finite family of quadratics. In the case of higher order MRFs, with 2 × 2 cliques, we use an adaptive state space to handle the increased complexity. Extensive experiments demonstrate the power of learned models, the benefits of higher-order MRFs and the practicality of BP for these problems with the use of simple principled approximations.