brendt.wohlberg.net
HomePublications
› Publications
› Software

Cite Details

Brendt Wohlberg, "Convolutional Sparse Representations with Gradient Penalties", arXiv, 1705.04407, 2017

Abstract

While convolutional sparse representations enjoy a number of useful properties, they have received limited attention for image reconstruction problems. The present paper compares the performance of block-based and convolutional sparse representations in the removal of Gaussian white noise. While the usual formulation of the convolutional sparse coding problem is slightly inferior to the block-based representations in this problem, the performance of the convolutional form can be boosted beyond that of the block-based form by the inclusion of suitable penalties on the gradients of the coefficient maps.

BibTeX Entry

@techreport{wohlberg-2017-convolutional,
author = {Brendt Wohlberg},
title = {Convolutional Sparse Representations with Gradient Penalties},
year = {2017},
month = May,
urlpdf = {http://arxiv.org/pdf/1705.04407},
urlhtml = {http://arxiv.org/abs/1705.04407},
urlcode = {http://brendt.wohlberg.net/software/SPORCO/},
institution = {arXiv},
number = {1705.04407}
}