Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision

1 code implementation • 1 Feb 2022 • Patrick M. Jensen, Niels Jeppesen, Anders B. Dahl, Vedrana A. Dahl

We focus on generic algorithms, i. e., for unstructured graphs, but also compare with the specialized GridCut implementation.

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

no code implementations • ICCV 2021 • Niels Jeppesen, Patrick M. Jensen, Anders N. Christensen, Anders B. Dahl, Vedrana A. Dahl

We introduce a parallel version of the Quadratic Pseudo-Boolean Optimization (QPBO) algorithm for solving binary optimization tasks, such as image segmentation.

Image Segmentation Segmentation +1

Sparse Layered Graphs for Multi-Object Segmentation

1 code implementation • CVPR 2020 • Niels Jeppesen, Anders N. Christensen, Vedrana A. Dahl, Anders B. Dahl

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.

Object Segmentation +1