Pushing the Limits for View Prediction in Video Coding

Jens Ogniewski, Per-Erik Forssén

2017

Abstract

More and more devices have depth sensors, making RGB+D video data increasingly common. Depth images have also been considered for 3D and free-viewpoint video coding. This depth data can be used to render a given scene from different viewpoints, thus making it a useful asset in e.g. view prediction for video coding. In this paper we evaluate a multitude of algorithms for scattered data interpolation, in order to optimize the performance of frame prediction for video coding. Our evaluation uses the depth extension of the Sintel datasets. Using ground-truth sequences is crucial for such an optimization, as it ensures that all errors and artifacts are caused by the prediction itself rather than noisy or erroneous data. We also present a comparison with the commonly used mesh-based projection.

Paper Citation

in Harvard Style

Ogniewski J. and Forssén P. (2017). Pushing the Limits for View Prediction in Video Coding . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 68-76. DOI: 10.5220/0006131500680076

in Bibtex Style

@conference{visapp17,
author={Jens Ogniewski and Per-Erik Forssén},
title={Pushing the Limits for View Prediction in Video Coding},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={68-76},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006131500680076},
isbn={978-989-758-225-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - Pushing the Limits for View Prediction in Video Coding
SN - 978-989-758-225-7
AU - Ogniewski J.
AU - Forssén P.
PY - 2017
SP - 68
EP - 76
DO - 10.5220/0006131500680076