Products of ``Edge-Perts
Abstract
Images represent an important and abundant source of data. Understanding their statistical structure has important applications such as image compression and restoration. In this paper we propose a particular kind of probabilistic model, dubbed the "products of edge-perts model" to describe the structure of wavelet transformed images. We develop a practical denoising algorithm based on a single edge-pert and show state-ofthe-art denoising performance on benchmark images.
Cite
Text
Welling and Gehler. "Products of ``Edge-Perts." Neural Information Processing Systems, 2005.Markdown
[Welling and Gehler. "Products of ``Edge-Perts." Neural Information Processing Systems, 2005.](https://mlanthology.org/neurips/2005/welling2005neurips-products/)BibTeX
@inproceedings{welling2005neurips-products,
title = {{Products of ``Edge-Perts}},
author = {Welling, Max and Gehler, Peter V.},
booktitle = {Neural Information Processing Systems},
year = {2005},
pages = {419-426},
url = {https://mlanthology.org/neurips/2005/welling2005neurips-products/}
}