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

facebooktwittermailshare

FAST AND LIGHTWEIGHT IMAGE SUPER-RESOLUTION BASED ON DENSE RESIDUALS TWO-CHANNEL NETWORK

Abstract: 

The existing advanced super-resolution methods with deepening or widening network demand high computational resources and memory consumption. It is difficult to directly apply them in practice. Therefore, we propose a fast and lightweight two-channel end-to-end network with fewer parameters and low computational complexity in this paper. The shallow channel mainly restores the general outline of the image, while the deep channel mainly learns the high- frequency texture information. And the deep channel combines the dense block and residual connection. The dense block increases data flow of network, while the residual connection reduces the number of parameters and speeds up the convergence of network. Moreover, we propose an enhanced network using group convolution, which significantly reduces the parameters and computational complexity with slight performance loss. Our model has many fewer parameters and operations, and it is evaluated on different datasets, outperforming the current representative methods in accuracy and run time.

up
0 users have voted:

Paper Details

Authors:
Yonglian Shi, Sumei Li, Wen Li, Anqi Liu
Submitted On:
20 September 2019 - 5:29am
Short Link:
Type:
Poster
Event:
Paper Code:
1837
Document Year:
2019
Cite

Document Files

Yonglian Shi.pdf

(5)

Subscribe

[1] Yonglian Shi, Sumei Li, Wen Li, Anqi Liu, "FAST AND LIGHTWEIGHT IMAGE SUPER-RESOLUTION BASED ON DENSE RESIDUALS TWO-CHANNEL NETWORK", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4771. Accessed: Oct. 18, 2019.
@article{4771-19,
url = {http://sigport.org/4771},
author = {Yonglian Shi; Sumei Li; Wen Li; Anqi Liu },
publisher = {IEEE SigPort},
title = {FAST AND LIGHTWEIGHT IMAGE SUPER-RESOLUTION BASED ON DENSE RESIDUALS TWO-CHANNEL NETWORK},
year = {2019} }
TY - EJOUR
T1 - FAST AND LIGHTWEIGHT IMAGE SUPER-RESOLUTION BASED ON DENSE RESIDUALS TWO-CHANNEL NETWORK
AU - Yonglian Shi; Sumei Li; Wen Li; Anqi Liu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4771
ER -
Yonglian Shi, Sumei Li, Wen Li, Anqi Liu. (2019). FAST AND LIGHTWEIGHT IMAGE SUPER-RESOLUTION BASED ON DENSE RESIDUALS TWO-CHANNEL NETWORK. IEEE SigPort. http://sigport.org/4771
Yonglian Shi, Sumei Li, Wen Li, Anqi Liu, 2019. FAST AND LIGHTWEIGHT IMAGE SUPER-RESOLUTION BASED ON DENSE RESIDUALS TWO-CHANNEL NETWORK. Available at: http://sigport.org/4771.
Yonglian Shi, Sumei Li, Wen Li, Anqi Liu. (2019). "FAST AND LIGHTWEIGHT IMAGE SUPER-RESOLUTION BASED ON DENSE RESIDUALS TWO-CHANNEL NETWORK." Web.
1. Yonglian Shi, Sumei Li, Wen Li, Anqi Liu. FAST AND LIGHTWEIGHT IMAGE SUPER-RESOLUTION BASED ON DENSE RESIDUALS TWO-CHANNEL NETWORK [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4771