We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The approach extends traditional Markov random field (MRF) models by learning potential functions over extended pixel neighborhoods. Field potentials are modeled using a Products-of-Experts framework that exploits nonlinear functions of many linear filter responses. In contrast to previous MRF approaches all parameters, including the linear filters themselves, are learned from training data. We demonstrate the capabilities of this Field of Experts model with two example applications, image denoising and image inpainting, which are implemented using a simple, approximate inference scheme. While the model is trained on a generic image database and is not tuned toward a specific application, we obtain results that compete with and even outperform specialized techniques.
Fields of Experts: a framework for learning image priors
2005-01-01
474476 byte
Conference paper
Electronic Resource
English
Optimal Learning High-Order Markov Random Fields Priors of Colour Image
Springer Verlag | 2007
|British Library Conference Proceedings | 2016
|British Library Online Contents | 1995
|British Library Online Contents | 2009
|Image-Based Rendering Using Image-Based Priors
British Library Online Contents | 2005
|