Issue No. 02 - Feb. (2014 vol. 20)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TVCG.2013.118
Bruce Merry , Dept. of Comput. Sci., Univ. of Cape Town, Cape Town, South Africa
James Gain , Dept. of Comput. Sci., Univ. of Cape Town, Cape Town, South Africa
Patrick Marais , Dept. of Comput. Sci., Univ. of Cape Town, Cape Town, South Africa
Modern laser range scanning campaigns produce extremely large point clouds, and reconstructing a triangulated surface thus requires both out-of-core techniques and significant computational power. We present a GPU-accelerated implementation of the moving least-squares (MLS) surface reconstruction technique. We believe this to be the first GPU-accelerated, out-of-core implementation of surface reconstruction that is suitable for laser range-scanned data. While several previous out-of-core approaches use a sweep-plane approach, we subdivide the space into cubic regions that are processed independently. This independence allows the algorithm to be parallelized using multiple GPUs, either in a single machine or a cluster. It also allows data sets with billions of point samples to be processed on a standard desktop PC. We show that our implementation is an order of magnitude faster than a CPU-based implementation when using a single GPU, and scales well to 8 GPUs.
Octrees, Surface reconstruction, Graphics processing units, Arrays, Indexes, Surface treatment, Approximation methods
B. Merry, J. Gain and P. Marais, "Moving Least-Squares Reconstruction of Large Models with GPUs," in IEEE Transactions on Visualization & Computer Graphics, vol. 20, no. 2, pp. 249-261, 2014.