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

facebooktwittermailshare

Super-resolution of Omnidirectional Images Using Adversarial Learning

Abstract: 

An omnidirectional image (ODI) enables viewers to look in every direction from a fixed point through a head-mounted display providing an immersive experience compared to that of a standard image. Designing immersive virtual reality systems with ODIs is challenging as they require high resolution content. In this paper, we study super-resolution for ODIs and propose an improved generative adversarial network based model which is optimized to handle the artifacts obtained in the spherical observational space. Specifically, we propose to use a fast PatchGAN discriminator, as it needs fewer parameters and improves the super-resolution at a fine scale. We also explore the generative models with adversarial learning by introducing a spherical-content specific loss function, called 360-SS. To train and test the performance of our proposed model we prepare a dataset of 4500 ODIs. Our results demonstrate the efficacy of the proposed method and identify new challenges in ODI super-resolution for future investigations.

up
0 users have voted:

Paper Details

Authors:
Aakanksha Rana, Aljosa Smolic
Submitted On:
30 September 2019 - 3:45am
Short Link:
Type:
Poster
Event:
Document Year:
2019
Cite

Document Files

vsense_poster_template (3).pdf

(12)

Subscribe

[1] Aakanksha Rana, Aljosa Smolic, "Super-resolution of Omnidirectional Images Using Adversarial Learning ", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4849. Accessed: Oct. 18, 2019.
@article{4849-19,
url = {http://sigport.org/4849},
author = {Aakanksha Rana; Aljosa Smolic },
publisher = {IEEE SigPort},
title = {Super-resolution of Omnidirectional Images Using Adversarial Learning },
year = {2019} }
TY - EJOUR
T1 - Super-resolution of Omnidirectional Images Using Adversarial Learning
AU - Aakanksha Rana; Aljosa Smolic
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4849
ER -
Aakanksha Rana, Aljosa Smolic. (2019). Super-resolution of Omnidirectional Images Using Adversarial Learning . IEEE SigPort. http://sigport.org/4849
Aakanksha Rana, Aljosa Smolic, 2019. Super-resolution of Omnidirectional Images Using Adversarial Learning . Available at: http://sigport.org/4849.
Aakanksha Rana, Aljosa Smolic. (2019). "Super-resolution of Omnidirectional Images Using Adversarial Learning ." Web.
1. Aakanksha Rana, Aljosa Smolic. Super-resolution of Omnidirectional Images Using Adversarial Learning [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4849