loading
Documents

Research.Publish.Connect.

Paper

Authors: Vida Fakour-Sevom 1 ; Esin Guldogan 2 and Joni-Kristian Kämäräinen 3

Affiliations: 1 Nokia Technologies and Tampere University of Technology, Finland ; 2 Nokia Technologies, Finland ; 3 Tampere University of Technology, Finland

ISBN: 978-989-758-290-5

Keyword(s): Super-resolution, Virtual Reality, Equirectangular Panorama, Deep Convolutional Neural Network.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Image Enhancement and Restoration ; Image Formation and Preprocessing

Abstract: We propose deep convolutional neural network (CNN) based super-resolution for 360 (equirectangular) panorama images used by virtual reality (VR) display devices (e.g. VR glasses). Proposed super-resolution adopts the recent CNN architecture proposed in (Dong et al., 2016) and adapts it for equirectangular panorama images which have specific characteristics as compared to standard cameras (e.g. projection distortions). We demonstrate how adaptation can be performed by optimizing the trained network input size and fine-tuning the network parameters. In our experiments with 360 panorama images of rich natural content CNN based super-resolution achieves average PSNR improvement of 1.36 dB over the baseline (bicubic interpolation) and 1.56 dB by our equirectangular specific adaptation.

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.238.62.144

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Fakour-Sevom, V.; Guldogan, E. and Kämäräinen, J. (2018). 360 Panorama Super-resolution using Deep Convolutional Networks.In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-290-5, pages 159-165. DOI: 10.5220/0006618901590165

@conference{visapp18,
author={Vida Fakour{-}Sevom. and Esin Guldogan. and Joni{-}Kristian Kämäräinen.},
title={360 Panorama Super-resolution using Deep Convolutional Networks},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2018},
pages={159-165},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006618901590165},
isbn={978-989-758-290-5},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - 360 Panorama Super-resolution using Deep Convolutional Networks
SN - 978-989-758-290-5
AU - Fakour-Sevom, V.
AU - Guldogan, E.
AU - Kämäräinen, J.
PY - 2018
SP - 159
EP - 165
DO - 10.5220/0006618901590165

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.