Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Efficient volumetric anisotropic diffusion computation on GPUs

: Kuijper, Arjan


Alber, H.-D.:
83rd Annual Meeting of the International Association of Applied Mathematics and Mechanics (GAMM). Special issue : March 26-30, 2012, Darmstadt, Germany
Weinheim: Wiley-VCH, 2012 (Proceedings in applied mathematics and mechanics 12.2012, Nr.1)
International Association of Applied Mathematics and Mechanics (GAMM Annual Meeting) <83, 2012, Darmstadt>
Konferenzbeitrag, Zeitschriftenaufsatz
Fraunhofer IGD ()
partial differential equation; 3D data representation; 3D graphics; 3D image acquisition; 3D image processing; smoothing; scale space; Business Field: Virtual engineering; Research Area: Confluence of graphics and vision; Forschungsgruppe Capturing Reality (CARE)

We present an efficient implementation of volumetric 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. Our most complex volumetric anisotropic diffusion gains a speed up of more than 600 compared to a CPU solution [1].