A convex relaxation for multi-graph matching


  • P. Swoboda
  • D. Kainmüller
  • A. Mokarian
  • C. Theobalt
  • F. Bernard


  • Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition


  • Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 11148-11157


  • 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.