Parallel and Distributed Vision Algorithms Using Dual Decomposition

Petter Strandmark, Fredrik Kahl, Thomas Schoenemann

Research output: Contribution to journalArticlepeer-review

7 Citations (SciVal)


We investigate dual decomposition approaches for optimization problems arising in low-level vision. Dual decomposition can be used to parallelize existing algorithms, reduce memory requirements and to obtain approximate solutions of hard problems. An extensive set of experiments are performed for a variety of application problems including graph cut segmentation, curvature regularization and more generally the optimization of MRFs. We demonstrate that the technique can be useful for desktop computers, graphical processing units and supercomputer clusters. To facilitate further research, an implementation of the decomposition methods is made publicly available.
Original languageEnglish
Pages (from-to)1721-1732
JournalComputer Vision and Image Understanding
Issue number12
Publication statusPublished - 2011

Subject classification (UKÄ)

  • Mathematics
  • Computer Vision and Robotics (Autonomous Systems)


  • Graph cuts
  • Dual decomposition
  • Parallel
  • MRF
  • MPI
  • GPU


Dive into the research topics of 'Parallel and Distributed Vision Algorithms Using Dual Decomposition'. Together they form a unique fingerprint.

Cite this