The Community for Technology Leaders
2016 International Conference on Big Data and Smart Computing (BigComp) (2016)
Hong Kong, China
Jan. 18, 2016 to Jan. 20, 2016
ISSN: 2375-9356
ISBN: 978-1-4673-8795-8
pp: 137-142
Yeo-Jin Yoon , Department of Computer Science and Engineering, Sejong University, Seoul, Republic of Korea
Alexander Lelidis , TU Berlin, Germany
A. Cengiz Oztireli , Computer Graphics Laboratory, ETH Zürich, Switzerland
Jung-Min Hwang , Department of Computer Science and Engineering, Sejong University, Seoul, Republic of Korea
Markus Gross , Computer Graphics Laboratory, ETH Zürich, Switzerland
Soo-Mi Choi , Department of Computer Science and Engineering, Sejong University, Seoul, Republic of Korea
ABSTRACT
Geometry data in massive amounts can be generated thanks to the modern capture devices and mature geometry modeling tools. It is essential to develop the tools to analyze and utilize this big data. In this paper, we present an exploration of analyzing geometries via learning local geometry features. After extracting local geometry patches, we parameterize each patch geometry by a radial basis function based interpolation. We use the resulting coefficients as discrete representations of the patches. These are then fed into feature learning algorithms to extract the dominant components explaining the overall patch database. This simple approach allows us to handle general representations such as point clouds or meshes with noise, outliers, and missing data. We present features learned on several patch databases to illustrate the utility of such an analysis for geometry processing applications.
INDEX TERMS
Geometry, Dictionaries, Three-dimensional displays, Atomic measurements, Shape, Feature extraction, Image reconstruction
CITATION

Yeo-Jin Yoon, A. Lelidis, A. C. Oztireli, Jung-Min Hwang, M. Gross and Soo-Mi Choi, "Geometry representations with unsupervised feature learning," 2016 International Conference on Big Data and Smart Computing (BigComp)(BIGCOMP), Hong Kong, China, 2016, pp. 137-142.
doi:10.1109/BIGCOMP.2016.7425812
235 ms
(Ver 3.3 (11022016))