Unstructured point cloud surface denoising and decimation using distance RBF K-nearest neighbor Kernel

Authors:
Rixio Morales;Yunhong Wang;Zhaoxiang Zhang
Affiliations:
Beihang University, Department of Computer Science and Engineering, Beijing, China;Beihang University, Department of Computer Science and Engineering, Beijing, China;Beihang University, Department of Computer Science and Engineering, Beijing, China
Venue:
PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
Year:
2010

Citing 11
Cited 2

A signal processing approach to fair surface design

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
The quickhull algorithm for convex hulls

ACM Transactions on Mathematical Software (TOMS)
The approximation power of moving least-squares

Mathematics of Computation
Implicit fairing of irregular meshes using diffusion and curvature flow

Proceedings of the 26th annual conference on Computer graphics and interactive techniques
An Algorithm for Finding Best Matches in Logarithmic Expected Time

ACM Transactions on Mathematical Software (TOMS)
A survey of methods for recovering quadrics in triangle meshes

ACM Computing Surveys (CSUR)
A two-dimensional interpolation function for irregularly-spaced data

ACM '68 Proceedings of the 1968 23rd ACM national conference
Bilateral mesh denoising

ACM SIGGRAPH 2003 Papers
A survey of point-based techniques in computer graphics

Computers and Graphics
GPU-Accelerated Nearest Neighbor Search for 3D Registration

ICVS '09 Proceedings of the 7th International Conference on Computer Vision Systems: Computer Vision Systems
Robust Feature-Preserving Mesh Denoising Based on Consistent Subneighborhoods

IEEE Transactions on Visualization and Computer Graphics

Boundary extraction and simplification of a surface defined by a sparse 3D volume

Proceedings of the Third Symposium on Information and Communication Technology
Parameterization of point-cloud freeform surfaces using adaptive sequential learning RBFnetworks

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work unstructured point clouds, resulting from 3D range acquisition are point wise-processed, using a proposed kd-tree nearest neighbor method, based in a generative data driven, local radial basis function's (RBF) support:φ(S, pi(xi, yi, zi)), for the point set S : {pi}i∈I, using surface statistic and a Gaussian convolution kernel, point sets are smoothed according to local surface features. As a minor contribution we also present a point cloud semirigid grid decimation method, based on a similar framework, using multi-core hardware, experiment results achieve comparable quality results with existing and more complex methods; time performance and results are presented for comparison.