Template based shape descriptor

  • Authors:
  • Raif M. Rustamov

  • Affiliations:
  • Drew University, Madison, NJ

  • Venue:
  • EG 3DOR'09 Proceedings of the 2nd Eurographics conference on 3D Object Retrieval
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

We introduce a new 3D shape descriptor which maps the surface features onto an arbitrary template surface using mean-value interpolation. A compact numerical shape descriptor is extracted using manifold harmonics on the template. We show that mean-value interpolation is a strong alternative to the often used projection. The utility of using different templates is established by showing that concatenating descriptors coming from different templates improves retrieval quality.