PCPNet
Learning Local Shape Properties from Raw Point Clouds

1University College London        2LIX, École Polytechnique, CNRS
joint first authors

Eurographics 2018

We propose PCPNet, a deep-learning based approach for estimating local 3D shape properties in noisy point clouds, such as normals and curvature. PCPNet can estimate normals and curvature on a wide range of noise levels without parameters adjustments.


Abstract

PCPNET is a deep-learning based approach for estimating local 3D shape properties in point clouds. In contrast to the majority of prior techniques that concentrate on global or mid-level attributes, e.g., for shape classification or semantic labeling, we suggest a patch-based learning method, in which a series of local patches at multiple scales around eachpoint is encoded in a structured manner. Our approach is especially well-adapted for estimating local shape properties such as normals (both unoriented and oriented) and curvature from raw point clouds in the presence of strong noise and multi-scalefeatures. Our main contributions include both a novel multi-scale variant of the recently proposed PointNet architecture with emphasis on local shape information, and a series of novel applications in which we demonstrate how learning from trainingdata arising from well-structured triangle meshes, and applying the trained model to noisy point clouds can produce superior results compared to specialized state-of-the-art techniques. Finally, we demonstrate the utility of our approach in the context ofshape reconstruction, by showing how it can be used to extract normal orientation information from point clouds.


Bibtex
@article{GuerreroEtAl:PCPNet:2016,
  title   = {{PCPNet}: Learning Local Shape Properties from Raw Point Clouds}, 
  author  = {Paul Guerrero and Yanir Kleiman and Maks Ovsjanikov and Niloy J. Mitra},
  year    = {2018},
  journal = {Eurographics},
  volume = {},
  number = {},
  issn = {},
  pages = {},
  numpages = {},
  doi = {},
}
      
Acknowledgements

This work was supported by the ERC Starting Grants Smart-Geometry (StG-2013-335373) and EXPROTEA (StG-2017-758800), the Open3D Project (EPSRC Grant EP/M013685/1), the Chateaubriand Fellowship, chaire Jean Marjoulet from EcolePolytechnique, FUI project TANDEM 2, and a Google FocusedResearch Award.

Links

Paper (13.8MB)

Data (921MB)

Code

Slides (4.99MB)