English

Efficient Deformable Shape Correspondence via Kernel Matching

Computer Vision and Pattern Recognition 2017-09-18 v3

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. Surprisingly, in spite of the highly non-convex nature of the resulting quadratic assignment problem, our method converges to a semantically meaningful and continuous mapping in most of our experiments, and scales well. We provide preliminary theoretical analysis and several interpretations of the method.

Keywords

Cite

@article{arxiv.1707.08991,
  title  = {Efficient Deformable Shape Correspondence via Kernel Matching},
  author = {Zorah Lähner and Matthias Vestner and Amit Boyarski and Or Litany and Ron Slossberg and Tal Remez and Emanuele Rodolà and Alex Bronstein and Michael Bronstein and Ron Kimmel and Daniel Cremers},
  journal= {arXiv preprint arXiv:1707.08991},
  year   = {2017}
}

Comments

Accepted for oral presentation at 3DV 2017, including supplementary material