Robust and Accurate Line- And/or Point-Based Pose Estimation Without Manhattan Assumptions

Abstract

Usual Structure from Motion techniques based on feature points have a hard time on scenes with little texture or presenting a single plane, as in indoor environments. Line segments are more robust features in this case. We propose a novel geometrical criterion for two-view pose estimation using lines, that does not assume a Manhattan world. We also define a parameterless ( a contrario ) RANSAC-like method to discard calibration outliers and provide more robust pose estimations, possibly using points as well when available. Finally, we provide quantitative experimental data that illustrate failure cases of other methods and that show how our approach outperforms them, both in robustness and precision.

Cite

Text

Salaün et al. "Robust and Accurate Line- And/or Point-Based Pose Estimation Without Manhattan Assumptions." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46478-7_49

Markdown

[Salaün et al. "Robust and Accurate Line- And/or Point-Based Pose Estimation Without Manhattan Assumptions." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/salaun2016eccv-robust/) doi:10.1007/978-3-319-46478-7_49

BibTeX

@inproceedings{salaun2016eccv-robust,
  title     = {{Robust and Accurate Line- And/or Point-Based Pose Estimation Without Manhattan Assumptions}},
  author    = {Salaün, Yohann and Marlet, Renaud and Monasse, Pascal},
  booktitle = {European Conference on Computer Vision},
  year      = {2016},
  pages     = {801-818},
  doi       = {10.1007/978-3-319-46478-7_49},
  url       = {https://mlanthology.org/eccv/2016/salaun2016eccv-robust/}
}