360 panorama super-resolution using deep convolutional networks
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Details
| Original language | English |
|---|---|
| Title of host publication | VISIGRAPP 2018 - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications |
| Publisher | SCITEPRESS |
| Pages | 159-165 |
| Number of pages | 7 |
| Volume | 4 |
| ISBN (Electronic) | 9789897582905 |
| DOIs | |
| Publication status | Published - 2018 |
| Publication type | A4 Article in a conference publication |
| Event | INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS - Duration: 1 Jan 1900 → … |
Conference
| Conference | INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS |
|---|---|
| Period | 1/01/00 → … |
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.
ASJC Scopus subject areas
Keywords
- Deep convolutional neural network, Equirectangular panorama, Super-resolution, Virtual reality