activity
20142023
most citedInstanceCut: from Edges to Instances with MultiCut

23 citations · 65 across the 11 of their papers we have counts for

collaborators

10 papers

cs.CV20224 cited

A Comparative Study of Graph Matching Algorithms in Computer Vision

Stefan Haller, Lorenz Feineis, Lisa Hutschenreiter +5

The graph matching optimization problem is an essential component for many tasks in computer vision, such as bringing two deformable objects in correspondence. Naturally, a wide ra…

cs.CV20171 cited

A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching

Paul Swoboda, Carsten Rother, Hassan Abu Alhaija +2

We study the quadratic assignment problem, in computer vision also known as graph matching. Two leading solvers for this problem optimize the Lagrange decomposition duals with sub-…

cs.CV20176 cited

Global Hypothesis Generation for 6D Object Pose Estimation

Frank Michel, Alexander Kirillov, Eric Brachmann +4

This paper addresses the task of estimating the 6D pose of a known 3D object from a single RGB-D image. Most modern approaches solve this task in three steps: i) Compute local feat…

cs.CV20164 cited

Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling

Sebastian Ramos, Stefan Gehrig, Peter Pinggera +2

The detection of small road hazards, such as lost cargo, is a vital capability for self-driving cars. We tackle this challenging and rarely addressed problem with a vision system t…

cs.LG2016

Implicit Modeling -- A Generalization of Discriminative and Generative Approaches

Dmitrij Schlesinger, Carsten Rother

We propose a new modeling approach that is a generalization of generative and discriminative models. The core idea is to use an implicit parameterization of a joint probability dis…

cs.CV201623 cited

InstanceCut: from Edges to Instances with MultiCut

Alexander Kirillov, Evgeny Levinkov, Bjoern Andres +2

This work addresses the task of instance-aware semantic segmentation. Our key motivation is to design a simple method with a new modelling-paradigm, which therefore has a different…