Surface reconstruction is an important trend in 3D scanning. The problem is to recreate surfaces from a given point cloud within the shortest possible time and with a given quality criteria. There is a set of different approaches for solving this problem, which includes Self-Organized Maps, Bayesian reconstruction and Poisson reconstruction.
The aim of the research is to find the most suitable method based on Machine Learning unsupervised learning techniques for reconstruction of interior and exterior 3D scans of original objects. The self-organizing map type of the artificial neural network was chosen due to its ability to produce good results without restrictions on point cloud size and points’ order. It can generate meshes from a small number of point samples in an unorganized point cloud.
The purpose of this paper is to analyze and compare results obtained with the usage of two self-organizing map types – Surface Growing Neural Gas (sGNG) and Growing Cell Structures (GCS) reconstruction – for reconstruction of a 3D mesh from point cloud. In addition, the sGNG extension to multithreading is presented and compared to the original approach.