Fast parallel surface and solid voxelization on GPUs

Abstract

This paper presents data-parallel algorithms for surface and solid voxelization on graphics hardware. First, a novel conservative surface voxelization technique, setting all voxels overlapped by a mesh's triangles, is introduced, which is up to one order of magnitude faster than previous solutions leveraging the standard rasterization pipeline. We then show how the involved new triangle/box overlap test can be adapted to yield a 6-separating surface voxelization, which is thinner but still connected and gap-free. Complementing these algorithms, both a triangle-parallel and a tile-based technique for solid voxelization are subsequently presented. Finally, addressing the high memory consumption of high-resolution voxel grids, we introduce a novel octree-based sparse solid voxelization approach, where only close to the solid's boundary finest-level voxels are stored, whereas uniform interior and exterior regions are represented by coarser-level voxels. This representation is created directly from a mesh without requiring a full intermediate solid voxelization, enabling GPU-based voxelizations of unprecedented size.