Recovering correct reconstructions from indistinguishable geometry

Jared Heinly, Enrique Dunn, Jan Michael Frahm

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

7 Scopus citations

Abstract

Structure-from-motion (SFM) is widely utilized to generate 3D reconstructions from unordered photo-collections. However, in the presence of non unique, symmetric, or otherwise indistinguishable structure, SFM techniques often incorrectly reconstruct the final model. We propose a method that not only determines if an error is present, but automatically corrects the error in order to produce a correct representation of the scene. We find that by exploiting the co-occurrence information present in the scene's geometry, we can successfully isolate the 3D points causing the incorrect result. This allows us to split an incorrect reconstruction into error-free sub-models that we then correctly merge back together. Our experimental results show that our technique is efficient, robust to a variety of scenes, and outperforms existing methods.

Original languageEnglish
Title of host publicationProceedings - 2014 International Conference on 3D Vision, 3DV 2014
Pages377-384
Number of pages8
ISBN (Electronic)9781479970018
DOIs
StatePublished - 6 Feb 2015
Event2014 2nd International Conference on 3D Vision, 3DV 2014 - Tokyo, Japan
Duration: 8 Dec 201411 Dec 2014

Publication series

NameProceedings - 2014 International Conference on 3D Vision, 3DV 2014

Conference

Conference2014 2nd International Conference on 3D Vision, 3DV 2014
Country/TerritoryJapan
CityTokyo
Period8/12/1411/12/14

Keywords

  • 3D scene correction
  • Duplicate structure disambiguation
  • Local clustering coefficient
  • Structure from motion

Fingerprint

Dive into the research topics of 'Recovering correct reconstructions from indistinguishable geometry'. Together they form a unique fingerprint.

Cite this