Robust normal estimation for point clouds with sharp features

Bao Li, Ruwen Schnabel, Reinhard Klein, Zhiquan Cheng, Gang Dang, and Jin Shiyao
In: Computers & Graphics (Apr. 2010), 34:2(94-106)
 

Abstract

This paper presents a novel technique for estimating normals on unorganized point clouds. Methods from robust statistics are used to detect the best local tangent plane for each point. Therefore the algorithm is capable to deal with points located in high curvature regions or near/on complex sharp features, while being highly robust with respect to noise and outliers. In particular, the presented method reliably recovers sharp features but does not require tedious manual parameter tuning as done by current methods.

The key ingredients of our approach are a robust noise-scale estimator and a kernel density estimation (KDE) based objective function. In contrast to previous approaches the noise-scale estimation is not affected by sharp features and achieves high accuracy even in the presence of outliers. In addition, our normal estimation procedure allows detection and elimination of outliers. We confirm the validity and reliability of our approach on synthetic and measured data and demonstrate applications to point cloud denoising.

Keywords: Normal estimation, Outlier, Robust, Sharp feature

Paper available at http://www.sciencedirect.com/science/article/B6TYG-4Y9CF9M-2/2/6983f845587e63492436be6a95e3a2a5

Images

Bibtex

@ARTICLE{robustNormal,
    author = {Li, Bao and Schnabel, Ruwen and Klein, Reinhard and Cheng, Zhiquan and Dang, Gang and Shiyao, Jin},
     pages = {94--106},
     title = {Robust normal estimation for point clouds with sharp features},
   journal = {Computers {\&} Graphics},
    volume = {34},
    number = {2},
      year = {2010},
     month = apr,
      note = {http://www.sciencedirect.com/science/article/B6TYG-4Y9CF9M-2/2/6983f845587e63492436be6a95e3a2a5},
  keywords = {Normal estimation, Outlier, Robust, Sharp feature},
  abstract = {This paper presents a novel technique for estimating normals on unorganized point clouds. Methods
              from robust statistics are used to detect the best local tangent plane for each point. Therefore the
              algorithm is capable to deal with points located in high curvature regions or near/on complex sharp
              features, while being highly robust with respect to noise and outliers. In particular, the presented
              method reliably recovers sharp features but does not require tedious manual parameter tuning as done
              by current methods.
              
              The key ingredients of our approach are a robust noise-scale estimator and a kernel density
              estimation (KDE) based objective function. In contrast to previous approaches the noise-scale
              estimation is not affected by sharp features and achieves high accuracy even in the presence of
              outliers. In addition, our normal estimation procedure allows detection and elimination of outliers.
              We confirm the validity and reliability of our approach on synthetic and measured data and
              demonstrate applications to point cloud denoising.},
      issn = {0097-8493},
       doi = {10.1016/j.cag.2010.01.004}
}