Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo

Gottfried Graber; Jonathan Balzer; Stefano Soatto; Thomas Pock

CVPR 2015poster56 citations

Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo

Gottfried Graber, Jonathan Balzer, Stefano Soatto, Thomas Pock

Abstract

We propose a method for dense three-dimensional surface reconstruction that leverages the strengths of shape-based approaches, by imposing regularization that respects the geometry of the surface, and the strength of depth-map-based stereo, by avoiding costly computation of surface topology. The result is a near real-time variational reconstruction algorithm free of the staircasing artifacts that affect depth-map and plane-sweeping approaches. This is made possible by exploiting the gauge ambiguity to design a novel representation of the regularizer that is linear in the parameters and hence amenable to be optimized with state-of-the-art primal-dual numerical schemes.

BibTeX

@inproceedings{cvpr2015_efficientminimal,
  title = {Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo},
  author = {Gottfried Graber and Jonathan Balzer and Stefano Soatto and Thomas Pock},
  booktitle = {CVPR 2015},
  year = {2015}
}