GPU-based euclidean distance transforms and their application to volume rendering

Jens Schneider*, Martin Kraus, Rüdiger Westermann

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Citations (SciVal)

Abstract

We present discrete 2D and 3D distance transforms based on the vector propagation algorithm by Danielsson. Like other vector propagation algorithms, the proposed method is close to exact, i.e., the error can be strictly bounded from above and is significantly smaller than one pixel. Our contribution is that the algorithm runs entirely on consumer class graphics hardware, thereby achieving a throughput of up to 96 Mpixels/s. Therefore, the proposed method can be used in a wide range of applications that rely on both high speed and high quality. The usability of our approach is demonstrated in the context of hardware-accelerated volumetric isosurface raycasting.

Original languageEnglish (US)
Title of host publicationComputer Vision, Imaging and Computer Graphics
Subtitle of host publicationTheory and Applications - International Joint Conference, VISIGRAPP 2009, Revised Selected Papers
Pages215-228
Number of pages14
DOIs
StatePublished - Oct 11 2010
EventInternational Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2009 - Lisboa, Portugal
Duration: Feb 5 2009Feb 8 2009

Publication series

NameCommunications in Computer and Information Science
Volume68 CCIS
ISSN (Print)1865-0929

Other

OtherInternational Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2009
Country/TerritoryPortugal
CityLisboa
Period02/5/0902/8/09

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Fingerprint

Dive into the research topics of 'GPU-based euclidean distance transforms and their application to volume rendering'. Together they form a unique fingerprint.

Cite this