Towards Efficient and Exact MAP-Inference for Large Scale Discrete Computer Vision Problems via Combinatorial Optimization

no code implementations • CVPR 2013 • Jorg Hendrik Kappes, Markus Speth, Gerhard Reinelt, Christoph Schnorr

Discrete graphical models (also known as discrete Markov random fields) are a major conceptual tool to model the structure of optimization problems in computer vision.

Combinatorial Optimization Playing the Game of 2048

Higher-order Segmentation via Multicuts

no code implementations • 28 May 2013 • Joerg Hendrik Kappes, Markus Speth, Gerhard Reinelt, Christoph Schnoerr

Multicuts enable to conveniently represent discrete graphical models for unsupervised and supervised image segmentation, in the case of local energy functions that exhibit symmetries.

Image Segmentation Segmentation +1