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

facebooktwittermailshare

Guided CycleGAN via Semi-Dual Optimal Transport for Photo-Realistic Face Super-resolution

Abstract: 

Face super-resolution has been studied for decades, and many approaches have been proposed to upsample low-resolution face images using information mined from paired low-resolution (LR) images and high-resolution (HR) images. However, most of this kind of works only simply sharpen the blurry edges in the upsampled face images and typically no photo-realistic face is reconstructed in the final result. In this paper, we present a GAN-based algorithm for face super-resolution which properly synthesizes photo-realistic super-recovered face. To this end, we introduce semi-dual optimal transport to optimize our model such that the distribution of its generated data can match the distribution of a target domain as much as possible. This way would endow our model with learning the mapping of distribution from unpaired LR images and HR images with desired properties. We demonstrate the robustness of our algorithm by testing it on Color FERET database and show that its performance is considerably superior to all state-of-the-art approaches.

up
0 users have voted:

Paper Details

Authors:
Wenbo Zheng, Chao Gou, Lan Yan, Wenwen Zhang, Fei-Yue Wang
Submitted On:
11 September 2019 - 12:15am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Wenbo Zheng
Paper Code:
1480
Document Year:
2019
Cite

Document Files

Poster File

(29)

Subscribe

[1] Wenbo Zheng, Chao Gou, Lan Yan, Wenwen Zhang, Fei-Yue Wang, " Guided CycleGAN via Semi-Dual Optimal Transport for Photo-Realistic Face Super-resolution", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4586. Accessed: Dec. 13, 2019.
@article{4586-19,
url = {http://sigport.org/4586},
author = {Wenbo Zheng; Chao Gou; Lan Yan; Wenwen Zhang; Fei-Yue Wang },
publisher = {IEEE SigPort},
title = { Guided CycleGAN via Semi-Dual Optimal Transport for Photo-Realistic Face Super-resolution},
year = {2019} }
TY - EJOUR
T1 - Guided CycleGAN via Semi-Dual Optimal Transport for Photo-Realistic Face Super-resolution
AU - Wenbo Zheng; Chao Gou; Lan Yan; Wenwen Zhang; Fei-Yue Wang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4586
ER -
Wenbo Zheng, Chao Gou, Lan Yan, Wenwen Zhang, Fei-Yue Wang. (2019). Guided CycleGAN via Semi-Dual Optimal Transport for Photo-Realistic Face Super-resolution. IEEE SigPort. http://sigport.org/4586
Wenbo Zheng, Chao Gou, Lan Yan, Wenwen Zhang, Fei-Yue Wang, 2019. Guided CycleGAN via Semi-Dual Optimal Transport for Photo-Realistic Face Super-resolution. Available at: http://sigport.org/4586.
Wenbo Zheng, Chao Gou, Lan Yan, Wenwen Zhang, Fei-Yue Wang. (2019). " Guided CycleGAN via Semi-Dual Optimal Transport for Photo-Realistic Face Super-resolution." Web.
1. Wenbo Zheng, Chao Gou, Lan Yan, Wenwen Zhang, Fei-Yue Wang. Guided CycleGAN via Semi-Dual Optimal Transport for Photo-Realistic Face Super-resolution [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4586