A Hybrid CPU-GPU Scalable Strategy for Multi-resolution Rendering of Large Digital Elevation Models with Borders and Holes

Andrey Rodrigues, Waldemar Celes

2018

Abstract

Efficient rendering of large digital elevation models remains as a challenge for real-time applications, especially if those models contain irregular borders and holes. First, direct use of hardware tessellation has limited scalability; although the graphics hardware is capable of controlling the resolution of patches in a very efficient manner, the whole patch data must be loaded in memory. Second, previous techniques restrict elevation data resolution and do not handle irregular border or holes. In this paper, we propose an efficient and scalable hybrid CPU-GPU algorithm for rendering large digital elevation models. Our proposal effectively combines GPU tessellation with CPU tile management, taking full advantage of GPU processing capabilities while maintaining graphics-memory use under practical limits. Our proposal also handles models with irregular borders and holes. Additionally, we present a technique to manage level of detail of aerial imagery mapped on top of elevation models. Both geometry and texture level of detail management run independently, and tiles are combined with no need to load extra data.

Download


Paper Citation


in Harvard Style

Rodrigues A. and Celes W. (2018). A Hybrid CPU-GPU Scalable Strategy for Multi-resolution Rendering of Large Digital Elevation Models with Borders and Holes. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 1: GRAPP; ISBN 978-989-758-287-5, SciTePress, pages 240-247. DOI: 10.5220/0006621902400247


in Bibtex Style

@conference{grapp18,
author={Andrey Rodrigues and Waldemar Celes},
title={A Hybrid CPU-GPU Scalable Strategy for Multi-resolution Rendering of Large Digital Elevation Models with Borders and Holes},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 1: GRAPP},
year={2018},
pages={240-247},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006621902400247},
isbn={978-989-758-287-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 1: GRAPP
TI - A Hybrid CPU-GPU Scalable Strategy for Multi-resolution Rendering of Large Digital Elevation Models with Borders and Holes
SN - 978-989-758-287-5
AU - Rodrigues A.
AU - Celes W.
PY - 2018
SP - 240
EP - 247
DO - 10.5220/0006621902400247
PB - SciTePress