Search Results for author: Paul Swoboda

Found 19 papers, 11 papers with code

Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths

2 code implementations ICCV 2021 Andrea Hornakova, Timo Kaiser, Paul Swoboda, Michal Rolinek, Bodo Rosenhahn, Roberto Henschel

We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT).

Multiple Object Tracking

Lifted Disjoint Paths with Application in Multiple Object Tracking

1 code implementation ICML 2020 Andrea Hornakova, Roberto Henschel, Bodo Rosenhahn, Paul Swoboda

We present an extension to the disjoint paths problem in which additional \emph{lifted} edges are introduced to provide path connectivity priors.

Global Optimization Multiple Object Tracking

Exact MAP-Inference by Confining Combinatorial Search with LP Relaxation

1 code implementation14 Apr 2020 Stefan Haller, Paul Swoboda, Bogdan Savchynskyy

This property allows to significantly reduce the computational time of the combinatorial solver and therefore solve problems which were out of reach before.

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

3 code implementations25 Mar 2020 Michal Rolínek, Paul Swoboda, Dominik Zietlow, Anselm Paulus, Vít Musil, Georg Martius

Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers.

Combinatorial Optimization Graph Matching

Bottleneck potentials in Markov Random Fields

1 code implementation ICCV 2019 Ahmed Abbas, Paul Swoboda

We consider general discrete Markov Random Fields(MRFs) with additional bottleneck potentials which penalize the maximum (instead of the sum) over local potential value taken by the MRF-assignment.

Combinatorial Optimization

Higher-order Projected Power Iterations for Scalable Multi-Matching

no code implementations26 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.

MAP inference via Block-Coordinate Frank-Wolfe Algorithm

1 code implementation CVPR 2019 Paul Swoboda, Vladimir Kolmogorov

We present a new proximal bundle method for Maximum-A-Posteriori (MAP) inference in structured energy minimization problems.

Graph Matching

A Message Passing Algorithm for the Minimum Cost Multicut Problem

no code implementations CVPR 2017 Paul Swoboda, Bjoern Andres

We propose a dual decomposition and linear program relaxation of the NP -hard minimum cost multicut problem.

Maximum Persistency via Iterative Relaxed Inference with Graphical Models

no code implementations CVPR 2015 Alexander Shekhovtsov, Paul Swoboda, Bogdan Savchynskyy

We propose an efficient implementation, which runs in time comparable to a single run of a suboptimal dual solver.

Global MAP-Optimality by Shrinking the Combinatorial Search Area with Convex Relaxation

no code implementations NeurIPS 2013 Bogdan Savchynskyy, Jörg Hendrik Kappes, Paul Swoboda, Christoph Schnörr

We consider energy minimization for undirected graphical models, also known as MAP-inference problem for Markov random fields.

Convex Variational Image Restoration with Histogram Priors

no code implementations16 Jan 2013 Paul Swoboda, Christoph Schnörr

We present a novel variational approach to image restoration (e. g., denoising, inpainting, labeling) that enables to complement established variational approaches with a histogram-based prior enforcing closeness of the solution to some given empirical measure.

Denoising Image Restoration

Cannot find the paper you are looking for? You can Submit a new open access paper.