MPI-I-2004-4-005
Neural meshes: surface reconstruction with a learning algorithm
Ivrissimtzis, I.P. and Jeong, W.-K. and Lee, S. and Lee, Y. and and Seidel, H.-P.
October 2004, 22 pages.
.
Status: available - back from printing
In this paper we propose a Learning algorithm for surface
reconstruction. Our algorithm simulates an incrementally expanding
neural network which learns a point cloud through a competitive
learning process. The topology is learned through statistics based
operators which create boundaries and merge them to create handles. We
study the algorithm theoretically, analyzing statistically its main
components, and experimentally, using an extensive range of input data sets.
-
- Attachement: MPI-I-2004-4-005.pdf (3767 KBytes)
URL to this document: https://domino.mpi-inf.mpg.de/internet/reports.nsf/NumberView/2004-4-005
BibTeX
@TECHREPORT{IvrissimtzisJeongLeeLeeSeidel2004,
AUTHOR = {Ivrissimtzis, I.P. and Jeong, W.-K. and Lee, S. and Lee, Y. and and Seidel, H.-P.},
TITLE = {Neural meshes: surface reconstruction with a learning algorithm},
TYPE = {Research Report},
INSTITUTION = {Max-Planck-Institut f{\"u}r Informatik},
ADDRESS = {Stuhlsatzenhausweg 85, 66123 Saarbr{\"u}cken, Germany},
NUMBER = {MPI-I-2004-4-005},
MONTH = {October},
YEAR = {2004},
ISSN = {0946-011X},
}