Affine-Invariant Photometric Heat Kernel Signatures

Loading...
Thumbnail Image
Date
2012
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
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.
Description

        
@inproceedings{
:10.2312/3DOR/3DOR12/039-046
, booktitle = {
Eurographics Workshop on 3D Object Retrieval
}, editor = {
M. Spagnuolo and M. Bronstein and A. Bronstein and A. Ferreira
}, title = {{
Affine-Invariant Photometric Heat Kernel Signatures
}}, author = {
Kovnatsky, Artiom
and
Bronstein, Michael M.
and
Bronstein, Alexander M.
and
Raviv, Dan
and
Kimmel, Ron
}, year = {
2012
}, publisher = {
The Eurographics Association
}, ISSN = {
1997-0463
}, ISBN = {
978-3-905674-36-1
}, DOI = {
/10.2312/3DOR/3DOR12/039-046
} }
Citation
Collections