Affine-invariant diffusion geometry for the analysis of deformable 3D shapes

Authors:
D. Raviv;A. M. Bronstein;M. M. Bronstein;R. Kimmel;N. Sochen
Affiliations:
Dept. of Comput. Sci., Technion - Israel Inst. of Technol., Haifa, Israel;Dept. of Electr. Eng., Tel Aviv Univ., Tel Aviv, Israel;Dept. of Inf., Univ. della Svizzera Italiana, Lugano, Switzerland;Dept. of Comput. Sci., Technion - Israel Inst. of Technol., Haifa, Israel;Dept. of Appl. Math., Tel Aviv Univ., Tel Aviv, Israel
Venue:
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Year:
2011

Citing 0
Cited 5

Intrinsic local symmetries: a computational framework

EG 3DOR'12 Proceedings of the 5th Eurographics conference on 3D Object Retrieval
Affine-invariant photometric heat kernel signatures

EG 3DOR'12 Proceedings of the 5th Eurographics conference on 3D Object Retrieval
3D object classification using scale invariant heat kernels with collaborative classification

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Equi-affine invariant geometries of articulated objects

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
Enhanced pose normalization and matching of non-rigid objects based on support vector machine modelling

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce an (equi-)affine invariant diffusion geometry by which surfaces that go through squeeze and shear transformations can still be properly analyzed. The definition of an affine invariant metric enables us to construct an invariant Laplacian from which local and global geometric structures are extracted. Applications of the proposed framework demonstrate its power in generalizing and enriching the existing set of tools for shape analysis.