Skip to main navigation Skip to search Skip to main content

L1-penalized robust estimation for a class of inverse problems arising in multiview geometry

  • Université Paris-Est

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

Abstract

We propose a new approach to the problem of robust estimation in multiview geometry. Inspired by recent advances in the sparse recovery problem of statistics, we define our estimator as a Bayesian maximum a posteriori with multivariate Laplace prior on the vector describing the outliers. This leads to an estimator in which the fidelity to the data is measured by the L -norm while the regularization is done by the L 1-norm. The proposed procedure is fairly fast since the outlier removal is done by solving one linear program (LP). An important difference compared to existing algorithms is that for our estimator it is not necessary to specify neither the number nor the proportion of the outliers. We present strong theoretical results assessing the accuracy of our procedure, as well as a numerical example illustrating its efficiency on real data.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference
PublisherNeural Information Processing Systems
Pages441-449
Number of pages9
ISBN (Print)9781615679119
Publication statusPublished - 1 Jan 2009
Externally publishedYes
Event23rd Annual Conference on Neural Information Processing Systems, NIPS 2009 - Vancouver, BC, Canada
Duration: 7 Dec 200910 Dec 2009

Publication series

NameAdvances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference

Conference

Conference23rd Annual Conference on Neural Information Processing Systems, NIPS 2009
Country/TerritoryCanada
CityVancouver, BC
Period7/12/0910/12/09

Fingerprint

Dive into the research topics of 'L1-penalized robust estimation for a class of inverse problems arising in multiview geometry'. Together they form a unique fingerprint.

Cite this