Canonical and Compact Point Cloud Representation for Shape Classification

We present a novel compact point cloud representation that is inherently invariant to scale, coordinate change and point permutation. The key idea is to parametrize a distance field around an individual shape into a unique, canonical, and compact vector in an unsupervised manner. We firstly project...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2018-09
Hauptverfasser:	Fujiwara, Kent, Sato, Ikuro, Ambai, Mitsuru, Yoshida, Yuichi, Sakakura, Yoshiaki
Format:	Artikel
Sprache:	eng
Schlagworte:	Neural networks Parameters Permutations Representations Singular value decomposition
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!