Fast remote isosurface visualization with chessboarding
EG PGV'04 Proceedings of the 5th Eurographics conference on Parallel Graphics and Visualization
| Hi-index | 0.00 |
The reconstruction of isosurfaces from scalar volume data has positioneditself as a fundamental visualization technique in many differentapplications. But the dramatically increasing size of volumetricdata sets often prohibits the handling of these models on affordablelow-end single processor architectures. Distributed client-serversystems integrating high-bandwidth transmission channelsand Web-based visualization tools are one alternative to attack thisparticular problem, but therefore new approaches to reduce the loadof numerical processing and the number of generated primitives arerequired. In this paper we outline different scenarios for distributedisosurface reconstruction from large-scale volumetric data sets. Wedemonstrate how to directly generate stripped surface representationsand we introduce adaptive and hierarchical concepts to minimizethe number of vertices that have to be reconstructed, transmittedand rendered. Furthermore, we propose a novel computationscheme, which allows the user to flexibly exploit locally availableresources. The proposed algorithms have been merged together inorder to build a platform-independent Web-based application. Extensiveuse of VRML and Java OpenGL-bindings allows for theexploration of large-scale volume data quite efficiently.