Self-Organizing Maps Application to Mesh Reconstruction
Surface reconstruction is an important trend in 3D scanning. There are different approaches to recreate surfaces from a given point cloud within the shortest possible time and with a given quality criteria. We’ll tell how to find the most suitable method based on Machine Learning unsupervised learning techniques for reconstruction of interior and exterior 3D scans of original objects. This presentation is about self-organizing maps algorithms and their use for surface reconstruction. We’ll focus on 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.
Technical Expert at AMC Bridge
Practically experienced in Parallel Computations, Machine Learning, 2D/3D graphics, Mobile Development