A Convex Formulation of Continuous Multi-label Problems

  • Authors:

  • Thomas Pock;Thomas Schoenemann;Gottfried Graber;Horst Bischof;Daniel Cremers

  • Affiliations:

  • Department of Computer Science, University of Bonn, and Institute for Computer Graphics and Vision, Graz University of Technology, ;Department of Computer Science, University of Bonn, ;Institute for Computer Graphics and Vision, Graz University of Technology, ;Institute for Computer Graphics and Vision, Graz University of Technology, ;Department of Computer Science, University of Bonn,

  • Venue:
  • ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose a spatially continuous formulation of Ishikawa's discrete multi-label problem. We show that the resulting non-convex variational problem can be reformulated as a convex variational problem via embedding in a higher dimensional space. This variational problem can be interpreted as a minimal surface problem in an anisotropic Riemannian space. In several stereo experiments we show that the proposed continuous formulation is superior to its discrete counterpart in terms of computing time, memory efficiency and metrication errors.