Affine-invariant photometric heat kernel signatures

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

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


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.

Original languageEnglish
Title of host publicationEG 3DOR 2012 - Eurographics 2012 Workshop on 3D Object Retrieval
Number of pages8
StatePublished - 2012
Externally publishedYes
Event5th Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2012 - Cagliari, Italy
Duration: 13 May 201213 May 2012

Publication series

NameEurographics Workshop on 3D Object Retrieval, EG 3DOR
ISSN (Print)1997-0463
ISSN (Electronic)1997-0471


Conference5th Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2012


Dive into the research topics of 'Affine-invariant photometric heat kernel signatures'. Together they form a unique fingerprint.

Cite this