Shape from Light Field meets Robust PCA

Stefan Heber, Thomas Pock

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

Abstract

In this paper we propose a new type of matching term for multi-view stereo reconstruction. Our model is based on the assumption, that if one warps the images of the various views to a common warping-center and considers each warped image as one row in a matrix, then this matrix will have low rank. This also implies, that we assume a certain amount of overlap between the views
after the warping has been performed. Such an assumption is obviously met in the case of light field data, which motivated us to demonstrate the proposed model for this type of data. Our final model is a large scale convex optimization problem, where the low rank minimization is relaxed via the nuclear norm. We present qualitative and quantitative experiments, where the proposed model achieves excellent results.
Originalspracheenglisch
TitelComputer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI
Herausgeber (Verlag)Springer International Publishing AG
Seiten751-767
Band8694
ISBN (elektronisch)978-3-319-10599-4
ISBN (Print)978-3-319-10598-7
DOIs
PublikationsstatusAngenommen/In Druck - 2014

    Fingerprint

Fields of Expertise

  • Information, Communication & Computing

Dieses zitieren

Heber, S., & Pock, T. (Angenommen/Im Druck). Shape from Light Field meets Robust PCA. in Computer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI (Band 8694, S. 751-767). Springer International Publishing AG . https://doi.org/10.1007/978-3-319-10599-4_48