Learning Sparse Multiscale Image Representations
Abstract
We describe a method for learning sparse multiscale image repre- sentations using a sparse prior distribution over the basis function coe(cid:14)cients. The prior consists of a mixture of a Gaussian and a Dirac delta function, and thus encourages coe(cid:14)cients to have exact zero values. Coe(cid:14)cients for an image are computed by sampling from the resulting posterior distribution with a Gibbs sampler. The learned basis is similar to the Steerable Pyramid basis, and yields slightly higher SNR for the same number of active coe(cid:14)cients. De- noising using the learned image model is demonstrated for some standard test images, with results that compare favorably with other denoising methods.
Cite
Text
Sallee and Olshausen. "Learning Sparse Multiscale Image Representations." Neural Information Processing Systems, 2002.Markdown
[Sallee and Olshausen. "Learning Sparse Multiscale Image Representations." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/sallee2002neurips-learning/)BibTeX
@inproceedings{sallee2002neurips-learning,
title = {{Learning Sparse Multiscale Image Representations}},
author = {Sallee, Phil and Olshausen, Bruno A.},
booktitle = {Neural Information Processing Systems},
year = {2002},
pages = {1351-1358},
url = {https://mlanthology.org/neurips/2002/sallee2002neurips-learning/}
}