Hide menu

Assessing Losses for Point Set Registration

Anderson C. M. Tavares, Felix Järemo Lawin, Per-Erik Forssén
Robotics and Automation Letters
Volume 5, Number 2, Pages 3360-3367
April 2020


This paper introduces a framework for evaluation of the losses used in point set registration. In order for a loss to be useful with a local optimizer, such as e.g. Levenberg-Marquardt, or expectation maximisation (EM), it must be monotonic with respect to the sought transformation. This motivates us to introduce monotonicity violation probability (MVP) curves, and use these to assess monotonicity empirically for many different local distances, such as point-to-point, point-to-plane, and plane-to-plane. We also introduce a local shape-to-shape distance, based on the Wasserstein distance of the local normal distributions. Evaluation is done on a comprehensive benchmark of terrestrial lidar scans from two publicly available datasets. It demonstrates that matching robustness can be improved significantly, by using kernel versions of local distances together with inverse density based sample weighting.

Full Paper

Preprint available from publisher at [DOI]

Bibtex entry

  author = {Anderson C. M Tavares and Felix J\"aremo Lawin and Per-Erik Forss\'en},
  title = {Assessing Losses for Point Set Registration},
  journal = 	 {Robotics and Automation Letters},
  year = 	 {2020},
  volume = 	 {5},
  number = 	 {2},
  pages = 	 {3360-3367},
  month = 	 {April},
  note = {Accepted 2020-02-03.},
  publisher =    {{IEEE}},
  url =          {https://doi.org/10.1109/LRA.2020.2976307}

Per-Erik Forssén

Per-Erik Forssén


Computer Vision Laboratory
Department of Electrical Engineering
Building B
Room 2D:521
SE-581 83 Linköping, Sweden
+46(0)13 285654

< >

My pages:

Page responsible: Per-Erik Forssén
Last updated: 2020-03-11