Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios

Abstract: 

The compressed sensing (CS) has been successfully applied to image compression in the past few years as most image signals are sparse in a certain domain. Several CS reconstruction models have been proposed and obtained superior performance. However, these methods suffer from blocking artifacts or ringing effects at low sampling ratios in most cases. To address this problem, we propose a deep convolutional Laplacian Pyramid Compressed Sensing Network (LapCSNet) for CS, which consists of a sampling sub-network and a reconstruction sub-network. In the sampling sub-network, we utilize a convolutional layer to mimic the sampling operator. In contrast to the fixed sampling matrices used in traditional CS methods, the filters used in our convolutional layer are jointly optimized with the reconstruction sub-network. In
the reconstruction sub-network, two branches are designed to reconstruct multi-scale residual images and muti-scale target images progressively using a Laplacian pyramid architecture. The proposed LapCSNet not only integrates multi-scale information to achieve better performance but also reduces computational cost dramatically. Experimental results on benchmark datasets demonstrate that the proposed method is capable of reconstructing more details and sharper edges against the state-of-the-arts methods.

up
1 user has voted: Wenxue Cui

Paper Details

Authors:
Wenxue Cui, Heyao Xu, Xinwei Gao, Shengping Zhang, Feng Jiang, Debin Zhao
Submitted On:
13 April 2018 - 1:16am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Feng Jiang
Document Year:
2018
Cite

Document Files

Compressed sensing, Convolutional neural network, CNN

(83 downloads)

Keywords

Additional Categories

Subscribe

[1] Wenxue Cui, Heyao Xu, Xinwei Gao, Shengping Zhang, Feng Jiang, Debin Zhao, "An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2600. Accessed: Sep. 24, 2018.
@article{2600-18,
url = {http://sigport.org/2600},
author = {Wenxue Cui; Heyao Xu; Xinwei Gao; Shengping Zhang; Feng Jiang; Debin Zhao },
publisher = {IEEE SigPort},
title = {An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios},
year = {2018} }
TY - EJOUR
T1 - An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios
AU - Wenxue Cui; Heyao Xu; Xinwei Gao; Shengping Zhang; Feng Jiang; Debin Zhao
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2600
ER -
Wenxue Cui, Heyao Xu, Xinwei Gao, Shengping Zhang, Feng Jiang, Debin Zhao. (2018). An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios. IEEE SigPort. http://sigport.org/2600
Wenxue Cui, Heyao Xu, Xinwei Gao, Shengping Zhang, Feng Jiang, Debin Zhao, 2018. An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios. Available at: http://sigport.org/2600.
Wenxue Cui, Heyao Xu, Xinwei Gao, Shengping Zhang, Feng Jiang, Debin Zhao. (2018). "An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios." Web.
1. Wenxue Cui, Heyao Xu, Xinwei Gao, Shengping Zhang, Feng Jiang, Debin Zhao. An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2600