Parameterization of point-cloud freeform surfaces using adaptive sequential learning RBFnetworks

We propose a self-organizing Radial Basis Function (RBF) neural network method for parameterization of freeform surfaces from larger, noisy and unoriented point clouds. In particular, an adaptive sequential learning algorithm is presented for network construction from a single instance of point set. The adaptive learning allows neurons to be dynamically inserted and fully adjusted (e.g. their locations, widths and weights), according to mapping residuals and data point novelty associated to underlying geometry. Pseudo-neurons, exhibiting very limited contributions, can be removed through a pruning procedure. Additionally, a neighborhood extended Kalman filter (NEKF) was developed to significantly accelerate parameterization. Experimental results show that this adaptive learning enables effective capture of global low-frequency variations while preserving sharp local details, ultimately leading to accurate and compact parameterization, as characterized by a small number of neurons. Parameterization using the proposed RBF network provides simple, low cost and low storage solutions to many problems such as surface construction, re-sampling, hole filling, multiple level-of-detail meshing and data compression from unstructured and incomplete range data. Performance results are also presented for comparison.

► Parametric representation of point-cloud freeform surfaces by adaptive RBF networks.
► Low cost and low storage on modeling larger, noisy and unstructured range scan data.
► High compression ratio achieved by a small number of neurons.
► Complete and smooth surface accurately reproduced from a compact network space.
► Efficient for mesh repair, multi-LODs and scattered data manipulation.