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

facebooktwittermailshare

PRED: A PARALLEL NETWORK FOR HANDLING MULTIPLE DEGRADATIONS VIA SINGLE MODEL IN SINGLE IMAGE SUPER-RESOLUTION

Abstract: 

Existing SISR (single image super-resolution) methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from its high-resolution (HR) counterpart, which inevitably give rise to poor performance when the degradation is out of assumption. To address this issue, we propose a framework PRED (parallel residual and encoder-decoder network) with an innovative training strategy to enhance the robustness to multiple degradations. Consequently, the network can handle spatially variant degradations, which significantly improves the practicability of the proposed method. Extensive experimental results on real LR images show that the proposed method can not only produce favorable results on multiple degradations, but also reconstruct visually plausible HR images.

up
1 user has voted: Guangyang Wu

Paper Details

Authors:
Guangyang Wu; Lili Zhao; Wenyi Wang; Liaoyuan Zeng; Jianwen Chen
Submitted On:
20 September 2019 - 7:16am
Short Link:
Type:
Poster
Event:
Presenter's Name:
吴广阳
Paper Code:
2707
Document Year:
2019
Cite

Document Files

PRED_poster

(16)

PRED_paper

(22)

Subscribe

[1] Guangyang Wu; Lili Zhao; Wenyi Wang; Liaoyuan Zeng; Jianwen Chen, "PRED: A PARALLEL NETWORK FOR HANDLING MULTIPLE DEGRADATIONS VIA SINGLE MODEL IN SINGLE IMAGE SUPER-RESOLUTION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4775. Accessed: Dec. 11, 2019.
@article{4775-19,
url = {http://sigport.org/4775},
author = {Guangyang Wu; Lili Zhao; Wenyi Wang; Liaoyuan Zeng; Jianwen Chen },
publisher = {IEEE SigPort},
title = {PRED: A PARALLEL NETWORK FOR HANDLING MULTIPLE DEGRADATIONS VIA SINGLE MODEL IN SINGLE IMAGE SUPER-RESOLUTION},
year = {2019} }
TY - EJOUR
T1 - PRED: A PARALLEL NETWORK FOR HANDLING MULTIPLE DEGRADATIONS VIA SINGLE MODEL IN SINGLE IMAGE SUPER-RESOLUTION
AU - Guangyang Wu; Lili Zhao; Wenyi Wang; Liaoyuan Zeng; Jianwen Chen
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4775
ER -
Guangyang Wu; Lili Zhao; Wenyi Wang; Liaoyuan Zeng; Jianwen Chen. (2019). PRED: A PARALLEL NETWORK FOR HANDLING MULTIPLE DEGRADATIONS VIA SINGLE MODEL IN SINGLE IMAGE SUPER-RESOLUTION. IEEE SigPort. http://sigport.org/4775
Guangyang Wu; Lili Zhao; Wenyi Wang; Liaoyuan Zeng; Jianwen Chen, 2019. PRED: A PARALLEL NETWORK FOR HANDLING MULTIPLE DEGRADATIONS VIA SINGLE MODEL IN SINGLE IMAGE SUPER-RESOLUTION. Available at: http://sigport.org/4775.
Guangyang Wu; Lili Zhao; Wenyi Wang; Liaoyuan Zeng; Jianwen Chen. (2019). "PRED: A PARALLEL NETWORK FOR HANDLING MULTIPLE DEGRADATIONS VIA SINGLE MODEL IN SINGLE IMAGE SUPER-RESOLUTION." Web.
1. Guangyang Wu; Lili Zhao; Wenyi Wang; Liaoyuan Zeng; Jianwen Chen. PRED: A PARALLEL NETWORK FOR HANDLING MULTIPLE DEGRADATIONS VIA SINGLE MODEL IN SINGLE IMAGE SUPER-RESOLUTION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4775