Automatic normal orientation in point clouds of building interiors

In: arXiv (2019)
 

Abstract

Orienting surface normals correctly and consistently is a fundamental problem in geometry processing. Applications such as visualization, feature detection, and geometry reconstruction often rely on the availability of correctly oriented normals. Many existing approaches for automatic orientation of normals on meshes or point clouds make severe assumptions on the input data or the topology of the underlying object which are not applicable to real-world measurements of urban scenes. In contrast, our approach is specifically tailored to the challenging case of unstructured indoor point cloud scans of multi-story, multi-room buildings. We evaluate the correctness and speed of our approach on multiple real-world point cloud datasets.

Images

Download Paper

Download Paper

Bibtex

@ARTICLE{Ochmann-2019-Orientation,
    author = {Ochmann, Sebastian and Klein, Reinhard},
     title = {Automatic normal orientation in point clouds of building interiors},
   journal = {arXiv},
      year = {2019},
  abstract = {Orienting surface normals correctly and consistently is a fundamental problem in geometry
              processing. Applications such as visualization, feature detection, and geometry reconstruction often
              rely on the availability of correctly oriented normals. Many existing approaches for automatic
              orientation of normals on meshes or point clouds make severe assumptions on the input data or the
              topology of the underlying object which are not applicable to real-world measurements of urban
              scenes. In contrast, our approach is specifically tailored to the challenging case of unstructured
              indoor point cloud scans of multi-story, multi-room buildings. We evaluate the correctness and speed
              of our approach on multiple real-world point cloud datasets.}
}