Efficient parallel optimization for potts energy with hierarchical fusion

  • Olga Veksler
  • Published 2015 in
    2015 IEEE Conference on Computer Vision and…

Abstract

Potts energy frequently occurs in computer vision applications. We present an efficient parallel method for optimizing Potts energy based on the extension of hierarchical fusion algorithm. Unlike previous parallel graph-cut based optimization algorithms, our approach has optimality bounds even after a single iteration over all labels, i.e. after solving… (More)
DOI: 10.1109/CVPR.2015.7298690

10 Figures and Tables

Topics

  • Presentations referencing similar topics