Volumetric nonlinear anisotropic diffusion on GPUs

  • Authors:
  • Andreas Schwarzkopf;Thomas Kalbe;Chandrajit Bajaj;Arjan Kuijper;Michael Goesele

  • Affiliations:
  • Technische Universität Darmstadt, Germany;Technische Universität Darmstadt, Germany;ICES-CVC University of Texas at Austin;Technische Universität Darmstadt, Germany;Technische Universität Darmstadt, Germany

  • Venue:
  • SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an efficient implementation of volumetric nonlinear anisotropic image diffusion on modern programmable graphics processing units (GPUs). We avoid the computational bottleneck of a time consuming eigenvalue decomposition in ℝ3. Instead, we use a projection of the Hessian matrix along the surface normal onto the tangent plane of the local isodensity surface and solve for the remaining two tangent space eigenvectors. We derive closed formulas to achieve this resulting in efficient GPU code. We show that our most complex volumetric nonlinear anisotropic diffusion gains a speed up of more than 600 compared to a CPU solution.