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

Gottfried Graber, Thomas Pock, Stefano Soatto, Jonathan Balzer

Research output: Chapter in Book/Report/Conference proceedingConference paper


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 depthmap-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.
Original languageEnglish
Title of host publicationThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publication statusPublished - 2015
EventCVPR 2015: CVPR 2015 - Boston, United States
Duration: 7 Jun 201512 Jun 2015


ConferenceCVPR 2015
Abbreviated titleCVPR 2015
CountryUnited States

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Application


Dive into the research topics of 'Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo'. Together they form a unique fingerprint.

Cite this