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

Gottfried Graber, Thomas Pock, Stefano Soatto, Jonathan Balzer

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

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 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.
Originalspracheenglisch
TitelThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Herausgeber (Verlag).
Seiten511-520
PublikationsstatusVeröffentlicht - 2015
Veranstaltung2015 IEEE Conference on Computer Vision and Pattern Recognition: CVPR 2015 - Boston, USA / Vereinigte Staaten
Dauer: 7 Juni 201512 Juni 2015

Konferenz

Konferenz2015 IEEE Conference on Computer Vision and Pattern Recognition
KurztitelCVPR 2015
Land/GebietUSA / Vereinigte Staaten
OrtBoston
Zeitraum7/06/1512/06/15

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Application

Fingerprint

Untersuchen Sie die Forschungsthemen von „Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren