Using a Depth Heuristic for Light Field Volume Rendering

Seán Martin, Seán Bruton, David Ganter, Michael Manzke

2019

Abstract

Existing approaches to light field view synthesis assume a unique depth in the scene. This assumption does not hold for an alpha-blended volume rendering. We propose to use a depth heuristic to overcome this limitation and synthesise views from one volume rendered sample view, which we demonstrate for an 8 × 8 grid. Our approach is comprised of a number of stages. Firstly, during direct volume rendering of the sample view, a depth heuristic is applied to estimate a per-pixel depth map. Secondly, this depth map is converted to a disparity map using the known virtual camera parameters. Then, image warping is performed using this disparity map to shift information from the reference view to novel views. Finally, these warped images are passed into a Convolutional Neural Network to improve visual consistency of the synthesised views. We evaluate multiple existing Convolutional Neural Network architectures for this purpose. Our application of depth heuristics is a novel contribution to light field volume rendering, leading to high quality view synthesis which is further improved by a Convolutional Neural Network.

Paper Citation

in Harvard Style

Martin S., Bruton S., Ganter D. and Manzke M. (2019). Using a Depth Heuristic for Light Field Volume Rendering. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 1: GRAPP; ISBN 978-989-758-354-4, SciTePress, pages 134-144. DOI: 10.5220/0007574501340144

in Bibtex Style

@conference{grapp19,
author={Seán Martin and Seán Bruton and David Ganter and Michael Manzke},
title={Using a Depth Heuristic for Light Field Volume Rendering},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 1: GRAPP},
year={2019},
pages={134-144},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007574501340144},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 1: GRAPP
TI - Using a Depth Heuristic for Light Field Volume Rendering
SN - 978-989-758-354-4
AU - Martin S.
AU - Bruton S.
AU - Ganter D.
AU - Manzke M.
PY - 2019
SP - 134
EP - 144
DO - 10.5220/0007574501340144
PB - SciTePress