Affordable Access

Access to the full text

Robust and Optimal Registration of Image Sets and Structured Scenes via Sum-of-Squares Polynomials

Authors
  • Paudel, Danda Pani1
  • Habed, Adlane2
  • Demonceaux, Cédric3
  • Vasseur, Pascal4
  • 1 ETH Zurich, Computer Vision Lab, Zurich, Switzerland , Zurich (Switzerland)
  • 2 University of Strasbourg, ICube Laboratory, CNRS, Strasbourg, France , Strasbourg (France)
  • 3 University of Bourgogne Franche-Comté, Le2i Laboratory, CNRS, Dijon, France , Dijon (France)
  • 4 Normandie Univ, UNIROUEN, UNIHAVRE, INSA Rouen, LITIS, Laboratoire d’Informatique, de Traitement de l’Information et des Systèmes, Rouen, 76000, France , Rouen (France)
Type
Published Article
Journal
International Journal of Computer Vision
Publisher
Springer-Verlag
Publication Date
Sep 11, 2018
Volume
127
Issue
5
Pages
415–436
Identifiers
DOI: 10.1007/s11263-018-1114-2
Source
Springer Nature
Keywords
License
Yellow

Abstract

This paper addresses the problem of registering a known structured 3D scene, typically a 3D scan, and its metric Structure-from-Motion (SfM) counterpart. The proposed registration method relies on a prior plane segmentation of the 3D scan. Alignment is carried out by solving either the point-to-plane assignment problem, should the SfM reconstruction be sparse, or the plane-to-plane one in case of dense SfM. A Polynomial Sum-of-Squares optimization theory framework is employed for identifying point-to-plane and plane-to-plane mismatches, i.e. outliers, with certainty. An inlier set maximization approach within a Branch-and-Bound search scheme is adopted to iteratively build potential inlier sets and converge to the solution satisfied by the largest number of assignments. Plane visibility conditions and vague camera locations may be incorporated for better efficiency without sacrificing optimality. The registration problem is solved in two cases: (i) putative correspondences (with possibly overwhelmingly many outliers) are provided as input and (ii) no initial correspondences are available. Our approach yields outstanding results in terms of robustness and optimality.

Report this publication

Statistics

Seen <100 times