169 citations · 422 across the 13 of their papers we have counts for
3 papers · 1 filter
DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems
Florian Bernard, Christian Theobalt, Michael Moeller
In this work we study convex relaxations of quadratic optimisation problems over permutation matrices. While existing semidefinite programming approaches can achieve remarkably tig…
Proximal Backpropagation
Thomas Frerix, Thomas Möllenhoff, Michael Moeller +1
We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network tr…
Nonlinear Spectral Image Fusion
Martin Benning, Michael Möller, Raz Z. Nossek +4
In this paper we demonstrate that the framework of nonlinear spectral decompositions based on total variation (TV) regularization is very well suited for image fusion as well as mo…