Tampere University of Technology

TUTCRIS Research Portal

360 panorama super-resolution using deep convolutional networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationVISIGRAPP 2018 - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
PublisherSCITEPRESS
Pages159-165
Number of pages7
Volume4
ISBN (Electronic)9789897582905
DOIs
Publication statusPublished - 2018
Publication typeA4 Article in a conference publication
EventINTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS -
Duration: 1 Jan 1900 → …

Conference

ConferenceINTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS
Period1/01/00 → …

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.

Keywords

  • Deep convolutional neural network, Equirectangular panorama, Super-resolution, Virtual reality

Publication forum classification

Field of science, Statistics Finland