Learning High-Order MRF Priors of Color Images
Abstract
In this paper, we use large neighborhood Markov random fields to learn rich prior models of color images. Our approach extends the monochromatic Fields of Experts model (Roth & Black, 2005a) to color images. In the Fields of Experts model, the curse of dimensionality due to very large clique sizes is circumvented by parameterizing the potential functions according to a product of experts. We introduce simplifications to the original approach by Roth and Black which allow us to cope with the increased clique size (typically 3x3x3 or 5x5x3 pixels) of color images. Experimental results are presented for image denoising which evidence improvements over state-of-the-art monochromatic image priors.
Cite
Text
McAuley et al. "Learning High-Order MRF Priors of Color Images." International Conference on Machine Learning, 2006. doi:10.1145/1143844.1143922Markdown
[McAuley et al. "Learning High-Order MRF Priors of Color Images." International Conference on Machine Learning, 2006.](https://mlanthology.org/icml/2006/mcauley2006icml-learning/) doi:10.1145/1143844.1143922BibTeX
@inproceedings{mcauley2006icml-learning,
title = {{Learning High-Order MRF Priors of Color Images}},
author = {McAuley, Julian J. and Caetano, Tibério S. and Smola, Alexander J. and Franz, Matthias O.},
booktitle = {International Conference on Machine Learning},
year = {2006},
pages = {617-624},
doi = {10.1145/1143844.1143922},
url = {https://mlanthology.org/icml/2006/mcauley2006icml-learning/}
}