MatchBox: Indoor image matching via box-like scene estimation

Filip Srajer, Alexander G. Schwing, Marc Pollefeys, Tomas Pajdla

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Keypoint matching in images of indoor scenes traditionally employs features like SIFT, GIST and HOG. While those features work very well for two images related to each other by small camera transformations, we commonly observe a drop in performance for patches representing scene elements visualized from a very different perspective. Since increasing the space of considered local transformations for feature matching decreases their discriminative abilities, we propose a more global approach inspired by the recent success of monocular scene understanding. In particular we propose to reconstruct a box-like model of the scene from every single image and use it to rectify images before matching. We show that a monocular scene model reconstruction and rectification preceding standard feature matching significantly improves keypoint matching and dramatically improves reconstruction of difficult indoor scenes.

Original languageEnglish (US)
Title of host publicationProceedings - 2014 International Conference on 3D Vision, 3DV 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages705-712
Number of pages8
ISBN (Electronic)9781479970018
DOIs
StatePublished - Feb 6 2015
Externally publishedYes
Event2014 2nd International Conference on 3D Vision, 3DV 2014 - Tokyo, Japan
Duration: Dec 8 2014Dec 11 2014

Publication series

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

Other

Other2014 2nd International Conference on 3D Vision, 3DV 2014
Country/TerritoryJapan
CityTokyo
Period12/8/1412/11/14

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'MatchBox: Indoor image matching via box-like scene estimation'. Together they form a unique fingerprint.

Cite this