A resource-allocating network for function interpolation
Neural Computation
Volumetric shape description of range data using “Blobby Model”
Proceedings of the 18th annual conference on Computer graphics and interactive techniques
A function estimation approach to sequential learning with neural networks
Neural Computation
Implicit reconstruction of solids from cloud point sets
SMA '95 Proceedings of the third ACM symposium on Solid modeling and applications
A Generalization of Algebraic Surface Drawing
ACM Transactions on Graphics (TOG)
Reconstruction and representation of 3D objects with radial basis functions
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Kalman Filtering and Neural Networks
Kalman Filtering and Neural Networks
Modelling with implicit surfaces that interpolate
ACM Transactions on Graphics (TOG)
A Multi-scale Approach to 3D Scattered Data Interpolation with Compactly Supported Basis Functions
SMI '03 Proceedings of the Shape Modeling International 2003
Multi-level partition of unity implicits
ACM SIGGRAPH 2003 Papers
Context-based surface completion
ACM SIGGRAPH 2004 Papers
IEEE Transactions on Neural Networks
Reformulated radial basis neural networks trained by gradient descent
IEEE Transactions on Neural Networks
Multiscale approximation with hierarchical radial basis functions networks
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
We present a novel adaptive radial basis function network to reconstruct smooth closed surfaces and complete meshes from non-uniformly sampled noisy range data. The network is established using a heuristic learning strategy. Neurons can be inserted, removed or updated iteratively, adapting to the complexity and distribution of the underlying data. This flexibility is particularly suited to highly variable spatial frequencies, and is conducive to data compression with network representations. In addition, a greedy neighbourhood Extended Kalman Filter learning method is investigated, leading to a significant reduction of computational cost in the training process with desired prediction accuracy. Experimental results demonstrate the performance advantages of compact network representation for surface reconstruction from large amount of non-uniformly sampled incomplete point-clouds.