Zorah Lähner

Zorah Lähner

Assistant Professor (tenure track), Geometry in Machine Learning Group

Efficient Deformable Shape Correspondence via Kernel Matching

Published in International Conference on 3D Vision (3DV), 2017

Matthias Vestner, Zorah Lähner, Amit Boyarski*, Or Litany, Ron Slossberg, Tal Remez, Emanuele Rodolà, Alex M. Bronstein, Michael M. Bronsteins, Ron Kimmel, Daniel Cremers

Teaser Image

Abstract

We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality. We formulate the problem as matching between a set of pair-wise and point-wise descriptors, imposing a continuity prior on the mapping, and propose a projected descent optimization procedure inspired by difference of convex functions (DC) programming.

Resources

[pdf] [arxiv] [github]

Bibtex

@InProceedings{vestner2017kernel,
    author = 	{M. Vestner and Z. L\"ahner and A. Boyarski and O. Litany and R. Slossberg and T. Remez and E. Rodol\`a and A. M. Bronstein and M. M. Bronstein and R. Kimmel and D. Cremers},
    title = 	{Efficient Deformable Shape Correspondence via Kernel Matching},
    booktitle=	{International Conference on 3D Vision (3DV)},
    year=	{2017},
    month=	{October},
}