A Polygonal Surface Reconstruction from Oriented Point Set

Abstract

We present a fast, memory efficient algorithm that reconstructs a manifold polygonal mesh approximately passing through a set of 3D oriented points. Nothing is assumed about the distribution of point set except that the point set is sampled from a real manifold surface. Our algorithm includes 3D convex hull, octree structure, SDF(signed distance function) for implicit framework, and marching cubes. The 3D convex hull provides us with a fast computation of SDF, octree structure allows us to compute a minimal distance for SDF, and marching cubes lead to iso-surface generation with SDF. Our approach gives us flexibility in the choice of the resolution of the reconstructed surface, and it also enables us to use on low-level PCs with minimal peak memory usage. Experimenting with publicly available scan data shows that we can reconstruct a polygonal mesh from point cloud of sizes varying from 10,000~1,000,000 in about 1~60 seconds on Intel(R) i7-7700K CPU @ 4.20 ㎓, 16 GB RAM.