Anders B. Dahl — accepted AI-conference papers

2021

Faster Multi-Object Segmentation Using Parallel Quadratic Pseudo-Boolean Optimization

Niels Jeppesen, Patrick M. Jensen, Anders N. Christensen, Anders B. Dahl, Vedrana A. Dahl

ICCV 2021poster

We introduce a parallel version of the Quadratic Pseudo-Boolean Optimization (QPBO) algorithm for solving binary optimization tasks, such as image segmentation. The original QPBO implementation by Kolmogorov and Rother relies on the Boykov-Kolmogorov (BK) maxflow/mincut algorithm and performs well f…

Cited by 3 PDF ↗Scholar ↗

2020

Sparse Layered Graphs for Multi-Object Segmentation

Niels Jeppesen, Anders N. Christensen, Vedrana A. Dahl, Anders B. Dahl

CVPR 2020poster

We introduce the novel concept of a Sparse Layered Graph (SLG) for s-t graph cut segmentation of image data. The concept is based on the widely used Ishikawa layered technique for multi-object segmentation, which allows explicit object interactions, such as containment and exclusion with margins. Ho…

Cited by 11 PDF ↗code ↗Scholar ↗