high performance computing on graphics processing units: hgpu.org

This paper presents an efficient and accurate isosurface rendering algorithm for the natural C^1 splines on the face-centered cubic (FCC) lattice. Leveraging fast and accurate evaluation of a spline field and its gradient, accompanied by efficient empty-space skipping, the approach generates high-quality isosurfaces of FCC datasets at interactive speed (20-70 fps). The pre-processing computation (quasi-interpolation and min/max cell construction) is improved 20 to 30-fold by OpenCL kernels. In addition, a novel indexing scheme is proposed that allows an FCC dataset to be stored as a four-channel 3D texture. When compared with other reconstruction schemes on the Cartesian and BCC (body-centered cubic) lattices, this method can be considered a practical reconstruction scheme that offers both quality and performance. The OpenCL and GLSL (OpenGL Shading Language) source codes are provided as a reference.