no code implementations • 20 Oct 2023 • Johan Thunberg, Florian Bernard
We propose a novel non-negative spherical relaxation for optimization problems over binary matrices with injectivity constraints, which in particular has applications in multi-matching and clustering.
no code implementations • NeurIPS 2021 • Florian Bernard, Daniel Cremers, Johan Thunberg
We address the non-convex optimisation problem of finding a sparse matrix on the Stiefel manifold (matrices with mutually orthogonal columns of unit length) that maximises (or minimises) a quadratic objective function.
no code implementations • CVPR 2021 • Maolin Gao, Zorah Lähner, Johan Thunberg, Daniel Cremers, Florian Bernard
Finding correspondences between shapes is a fundamental problem in computer vision and graphics, which is relevant for many applications, including 3D reconstruction, object tracking, and style transfer.
no code implementations • 26 Nov 2018 • Florian Bernard, Johan Thunberg, Paul Swoboda, Christian Theobalt
The matching of multiple objects (e. g. shapes or images) is a fundamental problem in vision and graphics.
no code implementations • 16 Mar 2018 • Florian Bernard, Johan Thunberg, Jorge Goncalves, Christian Theobalt
In order to deal with the inherent non-convexity of the permutation synchronisation problem, we use an initialisation procedure based on a novel rotation scheme applied to the solution of the spectral relaxation.
no code implementations • 25 Jan 2017 • Johan Thunberg, Florian Bernard, Jorge Goncalves
This paper addresses the problem of synchronizing orthogonal matrices over directed graphs.
no code implementations • CVPR 2017 • Florian Bernard, Frank R. Schmidt, Johan Thunberg, Daniel Cremers
We propose a combinatorial solution for the problem of non-rigidly matching a 3D shape to 3D image data.
1 code implementation • 26 Feb 2016 • Florian Bernard, Luis Salamanca, Johan Thunberg, Alexander Tack, Dennis Jentsch, Hans Lamecker, Stefan Zachow, Frank Hertel, Jorge Goncalves, Peter Gemmar
Estimating the parameters of the GMM in a maximum a posteriori manner yields the reconstruction of the surface from the given data points.
no code implementations • CVPR 2016 • Florian Bernard, Peter Gemmar, Frank Hertel, Jorge Goncalves, Johan Thunberg
Representing 3D shape deformations by linear models in high-dimensional space has many applications in computer vision and medical imaging, such as shape-based interpolation or segmentation.
no code implementations • 2 Sep 2015 • Johan Thunberg, Florian Bernard, Jorge Goncalves
Two direct or centralized synchronization methods are presented for different graph topologies; the first one for quasi-strongly connected graphs, and the second one for connected graphs.
no code implementations • CVPR 2015 • Florian Bernard, Johan Thunberg, Peter Gemmar, Frank Hertel, Andreas Husch, Jorge Goncalves
Simulations demonstrate that for noisy transformations, a large proportion of missing data and even for wrong correspondence assignments the method delivers encouraging results.