Volumetric heat kernel signatures

Dan Raviv, Michael M. Bronstein, Alexander M. Bronstein, Ron Kimmel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Invariant shape descriptors are instrumental in numerous shape analysis tasks including deformable shape comparison, registration, classification, and retrieval. Most existing constructions model a 3D shape as a two-dimensional surface describing the shape boundary, typically represented as a triangular mesh or a point cloud. Using intrinsic properties of the surface, invariant descriptors can be designed. One such example is the recently introduced heat kernel signature, based on the Laplace-Beltrami operator of the surface. In many applications, however, a volumetric shape model is more natural and convenient. Moreover, modeling shape deformations as approximate isometries of the volume of an object, rather than its boundary, better captures natural behavior of non-rigid deformations in many cases. Here, we extend the idea of heat kernel signature to robust isometry-invariant volumetric descriptors, and show their utility in shape retrieval. The proposed approach achieves state-of-the-art results on the SHREC 2010 large-scale shape retrieval benchmark.

Original languageEnglish
Title of host publication3DOR'10 - Proceedings of the 2010 ACM Workshop on 3D Object Retrieval, Co-located with ACM Multimedia 2010
Pages39-44
Number of pages6
DOIs
StatePublished - 2010
Externally publishedYes
Event2010 ACM Workshop on 3D Object Retrieval, 3DOR'10, Co-located with ACM Multimedia 2010 - Firenze, Italy
Duration: 25 Oct 201025 Oct 2010

Publication series

Name3DOR'10 - Proceedings of the 2010 ACM Workshop on 3D Object Retrieval, Co-located with ACM Multimedia 2010

Conference

Conference2010 ACM Workshop on 3D Object Retrieval, 3DOR'10, Co-located with ACM Multimedia 2010
Country/TerritoryItaly
CityFirenze
Period25/10/1025/10/10

Keywords

  • Heat kernel signature
  • Volumetric Laplacian

Fingerprint

Dive into the research topics of 'Volumetric heat kernel signatures'. Together they form a unique fingerprint.

Cite this