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

Martin R. Oswald, Daniel Cremers

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Scopus citations

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.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Computer Vision Workshops, ICCVW 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages291-298
Number of pages8
ISBN (Print)9781479930227
DOIs
StatePublished - 2013
Event2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013 - Sydney, NSW, Australia
Duration: 1 Dec 20138 Dec 2013

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Conference

Conference2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013
Country/TerritoryAustralia
CitySydney, NSW
Period1/12/138/12/13

Keywords

  • Convex relaxation
  • Multi-view reconstruction
  • Spatiotemporal

Fingerprint

Dive into the research topics of 'A convex relaxation approach to space time multi-view 3D reconstruction'. Together they form a unique fingerprint.

Cite this