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

Andrey Rodrigues, Waldemar Celes
2018 Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
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
more » ... s. 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.
doi:10.5220/0006621902400247 dblp:conf/grapp/RodriguesC18 fatcat:wtc3zf7iubfu3bjxad3dwgwv4e