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

facebooktwittermailshare

AN END-TO-END MULTI-SCALE RESIDUAL RECONSTRUCTION NETWORK FOR IMAGE COMPRESSIVE SENSING

Abstract: 

Recently, deep-learning based reconstruction models have been proposed to improve recovery performance of compressive sensed image and overcome expensive time complexity drawbacks of iteration-based traditional algorithms. In this paper, we propose an end-to-end multi-scale residual convolutional neural network (CNN), dubbed MSRNet, to simulate image compressive sensing (CS) and inverse reconstruction process in real situation. In MSRNet, we apply three parallel channels with different convolution kernel sizes to exploit different-scale feature information. Besides, global and local residual architecture are also introduced to accelerate training process and enhance prediction accuracy of network. Moreover, different from generating CS measurements by random measurement matrix in previous methods, we integrate compressive sample process into MSRNet, which means measurement matrix can be learned by training the network. Experiments on benchmark datasets show our method outperforms other state-of-the-art algorithms by large margins and set a new level for CS reconstruction with competitive time complexity.

up
0 users have voted:

Paper Details

Authors:
Sumei Li, Chunping Hou
Submitted On:
20 September 2019 - 8:10am
Short Link:
Type:
Poster
Event:
Paper Code:
2264
Document Year:
2019
Cite

Document Files

ID-TA.PF_.1.pdf

(8)

Subscribe

[1] Sumei Li, Chunping Hou, "AN END-TO-END MULTI-SCALE RESIDUAL RECONSTRUCTION NETWORK FOR IMAGE COMPRESSIVE SENSING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4777. Accessed: Oct. 18, 2019.
@article{4777-19,
url = {http://sigport.org/4777},
author = {Sumei Li; Chunping Hou },
publisher = {IEEE SigPort},
title = {AN END-TO-END MULTI-SCALE RESIDUAL RECONSTRUCTION NETWORK FOR IMAGE COMPRESSIVE SENSING},
year = {2019} }
TY - EJOUR
T1 - AN END-TO-END MULTI-SCALE RESIDUAL RECONSTRUCTION NETWORK FOR IMAGE COMPRESSIVE SENSING
AU - Sumei Li; Chunping Hou
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4777
ER -
Sumei Li, Chunping Hou. (2019). AN END-TO-END MULTI-SCALE RESIDUAL RECONSTRUCTION NETWORK FOR IMAGE COMPRESSIVE SENSING. IEEE SigPort. http://sigport.org/4777
Sumei Li, Chunping Hou, 2019. AN END-TO-END MULTI-SCALE RESIDUAL RECONSTRUCTION NETWORK FOR IMAGE COMPRESSIVE SENSING. Available at: http://sigport.org/4777.
Sumei Li, Chunping Hou. (2019). "AN END-TO-END MULTI-SCALE RESIDUAL RECONSTRUCTION NETWORK FOR IMAGE COMPRESSIVE SENSING." Web.
1. Sumei Li, Chunping Hou. AN END-TO-END MULTI-SCALE RESIDUAL RECONSTRUCTION NETWORK FOR IMAGE COMPRESSIVE SENSING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4777