A convex relaxation approach to space time multi-view 3D reconstruction

Martin R. Oswald, Daniel Cremers

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

16 Zitate (Scopus)

Abstract

We propose a convex relaxation approach to space-time 3D reconstruction from multiple videos. Generalizing the works Unger et al. [16], Kolev et al. [8] to the 4D setting, we cast the problem of reconstruction over time as a binary labeling problem in a 4D space. We propose a variational formulation which combines a photo consistency based data term with a spatio-temporal total variation regularization. In particular, we propose a novel data term that is both faster to compute and better suited for wide-baseline camera setups when photo consistency measures are unreliable or missing. The proposed functional can be globally minimized using convex relaxation techniques. Numerous experiments on a variety of public ally available data sets demonstrate that we can compute detailed and temporally consistent reconstructions. In particular, the temporal regularization allows to reduce jittering of voxels over time.

OriginalspracheEnglisch
TitelProceedings - 2013 IEEE International Conference on Computer Vision Workshops, ICCVW 2013
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten291-298
Seitenumfang8
ISBN (Print)9781479930227
DOIs
PublikationsstatusVeröffentlicht - 2013
Veranstaltung2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013 - Sydney, NSW, Australien
Dauer: 1 Dez. 20138 Dez. 2013

Publikationsreihe

NameProceedings of the IEEE International Conference on Computer Vision

Konferenz

Konferenz2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013
Land/GebietAustralien
OrtSydney, NSW
Zeitraum1/12/138/12/13

Fingerprint

Untersuchen Sie die Forschungsthemen von „A convex relaxation approach to space time multi-view 3D reconstruction“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren