MPI-I-2003-4-007
Neural meshes: statistical learning methods in surface reconstruction
Ivrissimtzis, Ioannis and Jeong, Won-Ki and Seidel, Hans-Peter
April 2003, 23 pages.
.
Status: available - back from printing
We propose a new surface reconstruction algorithm based on an
incrementally expanding neural network known as Growing Cell
Structure. The neural network learns a probability space, which
represents the surface for reconstruction, through a competitive
learning process. The topology is learned through statistics based
operations which create boundaries and merge them to create
handles. We study the algorithm theoretically, calculating its
complexity, using probabilistic arguments to find relationships
between the parameters, and finally, running statistical experiments
to optimize the parameters.
-
- Attachement: MPI-I-2003-4-007.pdf (2589 KBytes)
URL to this document: https://domino.mpi-inf.mpg.de/internet/reports.nsf/NumberView/2003-4-007
BibTeX
@TECHREPORT{IvrissimtzisJeongSeidel2003,
AUTHOR = {Ivrissimtzis, Ioannis and Jeong, Won-Ki and Seidel, Hans-Peter},
TITLE = {Neural meshes: statistical learning methods in surface reconstruction},
TYPE = {Research Report},
INSTITUTION = {Max-Planck-Institut f{\"u}r Informatik},
ADDRESS = {Stuhlsatzenhausweg 85, 66123 Saarbr{\"u}cken, Germany},
NUMBER = {MPI-I-2003-4-007},
MONTH = {April},
YEAR = {2003},
ISSN = {0946-011X},
}