TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

360 panorama super-resolution using deep convolutional networks

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoVISIGRAPP 2018 - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
KustantajaSCITEPRESS
Sivut159-165
Sivumäärä7
Vuosikerta4
ISBN (elektroninen)9789897582905
DOI - pysyväislinkit
TilaJulkaistu - 2018
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaINTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS -
Kesto: 1 tammikuuta 1900 → …

Conference

ConferenceINTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS
Ajanjakso1/01/00 → …

Tiivistelmä

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.