Affine-invariant photometric heat kernel signatures

  • Authors:
  • Artiom Kovnatsky;Michael M. Bronstein;Alexander M. Bronstein;Dan Raviv;Ron Kimmel

  • Affiliations:
  • Institute of Computational Science, Faculty of Informatics, Università della Svizzera Italiana, Lugano, Switzerland;Institute of Computational Science, Faculty of Informatics, Università della Svizzera Italiana, Lugano, Switzerland;School of Electrical Engineering, Tel Aviv University, Israel;Department of Computer Science, Technion, Israel Institute of Technology, Haifa, Israel;Department of Computer Science, Technion, Israel Institute of Technology, Haifa, Israel

  • Venue:
  • EG 3DOR'12 Proceedings of the 5th Eurographics conference on 3D Object Retrieval
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we explore the use of the diffusion geometry framework for the fusion of geometric and photometric information in local shape descriptors. Our construction is based on the definition of a modified metric, which combines geometric and photometric information, and then the diffusion process on the shape manifold is simulated. Experimental results show that such data fusion is useful in coping with shape retrieval experiments, where pure geometric and pure photometric methods fail. Apart from retrieval task the proposed diffusion process may be employed in other applications.