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

facebooktwittermailshare

CANNYGAN: Edge-PREserving image translation with disentangled features

Abstract: 

The image-to-image translation task often associates with the problem of missing texture and edge information. In this paper, we proposed a framework to translate images while preserving more realistic textures and details. To this end, we disentangle the samples into shared content space and domain-specific style domain. Then, according to the blurred outlines and textures in the source domain, we introduce the classic canny edge detection algorithm to encode the boundary and edge information in the content latent space. We test the proposed method in the thermal to visible image translation scenario and the experimental results demonstrate that the proposed method outperforms several other state-of-the-art models.

up
1 user has voted: Tianren Wang

Paper Details

Authors:
Tianren Wang, Teng Zhang, Liangchen Liu, Arnold Wiliem, Brian Lovell
Submitted On:
10 September 2019 - 9:12pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Tianren Wang
Paper Code:
3562
Document Year:
2019
Cite

Document Files

#3562_cannygan

(4)

Keywords

Additional Categories

Subscribe

[1] Tianren Wang, Teng Zhang, Liangchen Liu, Arnold Wiliem, Brian Lovell, "CANNYGAN: Edge-PREserving image translation with disentangled features", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4577. Accessed: Sep. 15, 2019.
@article{4577-19,
url = {http://sigport.org/4577},
author = {Tianren Wang; Teng Zhang; Liangchen Liu; Arnold Wiliem; Brian Lovell },
publisher = {IEEE SigPort},
title = {CANNYGAN: Edge-PREserving image translation with disentangled features},
year = {2019} }
TY - EJOUR
T1 - CANNYGAN: Edge-PREserving image translation with disentangled features
AU - Tianren Wang; Teng Zhang; Liangchen Liu; Arnold Wiliem; Brian Lovell
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4577
ER -
Tianren Wang, Teng Zhang, Liangchen Liu, Arnold Wiliem, Brian Lovell. (2019). CANNYGAN: Edge-PREserving image translation with disentangled features. IEEE SigPort. http://sigport.org/4577
Tianren Wang, Teng Zhang, Liangchen Liu, Arnold Wiliem, Brian Lovell, 2019. CANNYGAN: Edge-PREserving image translation with disentangled features. Available at: http://sigport.org/4577.
Tianren Wang, Teng Zhang, Liangchen Liu, Arnold Wiliem, Brian Lovell. (2019). "CANNYGAN: Edge-PREserving image translation with disentangled features." Web.
1. Tianren Wang, Teng Zhang, Liangchen Liu, Arnold Wiliem, Brian Lovell. CANNYGAN: Edge-PREserving image translation with disentangled features [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4577