Entropic metric alignment for correspondence problems

@article{Solomon2016EntropicMA,
  title={Entropic metric alignment for correspondence problems},
  author={Justin Solomon and Gabriel Peyr{\'e} and Vladimir G. Kim and Suvrit Sra},
  journal={ACM Trans. Graph.},
  year={2016},
  volume={35},
  pages={72:1-72:13}
}
Many shape and image processing tools rely on computation of correspondences between geometric domains. Efficient methods that stably extract "soft" matches in the presence of diverse geometric structures have proven to be valuable for shape retrieval and transfer of labels or semantic information. With these applications in mind, we present an algorithm for probabilistic correspondence that optimizes an entropy-regularized Gromov-Wasserstein (GW) objective. Built upon recent developments in… CONTINUE READING
Highly Cited
This paper has 42 citations. REVIEW CITATIONS

17 Figures & Tables

Topics

Statistics

0102030201620172018
Citations per Year

Citation Velocity: 16

Averaging 16 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.