論文

査読有り
2018年6月

An alternative visualization pipeline for large-scale data sets by using early visibility test point rendering

INTERNATIONAL JOURNAL OF MODELING SIMULATION AND SCIENTIFIC COMPUTING
  • Hideo Miyachi
  • ,
  • Daisuke Matsuoka
  • ,
  • Yoji Matsumoto

9
3
記述言語
英語
掲載種別
研究論文(学術雑誌)
DOI
10.1142/S1793962318400044
出版者・発行元
WORLD SCIENTIFIC PUBL CO PTE LTD

The amount of produced data required to be visualized and analyzed has grown year by year, and the traditional approach of using larger computational resources or exploiting task and data parallelism seems to have reached its limit. Therefore, a new paradigm for large-scale data visualization becomes highly desired, and in this paper, we propose a new and optimized visualization pipeline which uses a point rendering-based early visibility testing for reducing the unnecessary rendering in the final stage of the visualization pipeline, and we named this technique "Early Visibility Test Point Rendering". In a densely populated polygonal mesh scene, where multiple triangles may cover a single pixel, unnecessary and wasteful rendering will occur in the final stage of the traditional visualization pipeline, that is, during the rasterization process. Therefore, we propose an alternative visualization pipeline by introducing the "Early Visibility Test Point Rendering" for selecting only the visible polygonal elements for a given visualization scene. This visibility testing can be executed on the CPU side, and only the visible polygonal elements are needed to be sent to the GPU for an optimized rendering. We could verify the effectiveness of our proposed approach by using synthetic datasets, and also a real-world large-scale simulation result.

リンク情報
DOI
https://doi.org/10.1142/S1793962318400044
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000433197500005&DestApp=WOS_CPL
ID情報
  • DOI : 10.1142/S1793962318400044
  • ISSN : 1793-9623
  • eISSN : 1793-9615
  • Web of Science ID : WOS:000433197500005

エクスポート
BibTeX RIS