CVPR 2019oral55 citations
A Convex Relaxation for Multi-Graph Matching
Paul Swoboda, Dagmar Kainm"uller, Ashkan Mokarian, Christian Theobalt, Florian Bernard
Abstract
We present a convex relaxation for the multi-graph matching problem. Our formulation allows for partial pairwise matchings, guarantees cycle consistency, and our objective incorporates both linear and quadratic costs. Moreover, we also present an extension to higher-order costs. In order to solve the convex relaxation we employ a message passing algorithm that optimizes the dual problem. We experimentally compare our algorithm on established benchmark problems from computer vision, as well as on large problems from biological image analysis, the size of which exceed previously investigated multi-graph matching instances.
BibTeX
@inproceedings{cvpr2019_aconvexrelaxatio,
title = {A Convex Relaxation for Multi-Graph Matching},
author = {Paul Swoboda and Dagmar Kainm"uller and Ashkan Mokarian and Christian Theobalt and Florian Bernard},
booktitle = {CVPR 2019},
year = {2019}
}