Hassan Abu Alhaija — accepted AI-conference papers

2017

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

Paul Swoboda, Carsten Rother, Hassan Abu Alhaija, Dagmar Kainmuller, Bogdan Savchynskyy

CVPR 2017poster

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-gradient and dual ascent (also known as message passing) updates. We explore this direction further and propose several…

Cited by 68 PDF ↗code ↗Scholar ↗

2017

Bounding Boxes, Segmentations and Object Coordinates: How Important Is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?

Aseem Behl, Omid Hosseini Jafari, Siva Karthik Mustikovela, Hassan Abu Alhaija, Carsten Rother, Andreas Geiger

ICCV 2017poster

Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e.g., at texture-less or reflective surfaces. However, these challenges are omnipresent in dynamic road scenes, which is the focus of this work. Our main contribution is to overcome t…

Cited by 189 PDF ↗Scholar ↗