PointCNN: Convolution On X-Transformed Points

By Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen. 2018

2,957 citations recorded by the source corpus.

We present a simple and general framework for feature learning from point clouds. The key to the success of CNNs is the convolution operator that is capable of leveraging spatially-local correlation in data represented densely in grids (e.g. images). However, point clouds are irregular and unordered, thus directly convolving kernels against features associated with the points, will result in desertion of shape information and variance to point ordering. To address these problems, we propose to learn an $\mathcal{X}$-transformation from the input points, to simultaneously promote two causes. The first is the weighting of the input features associated with the points, and the second is the permutation of the points into a latent and potentially canonical order. Element-wise product and sum operations of the typical convolution operator are subsequently applied on the $\mathcal{X}$-transformed features. The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN. Experiments show that PointCNN achieves on par or better performance than state-of-the-art methods on multiple challenging benchmark datasets and tasks.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition, Geology, Model Architectures, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

  1. Hongsheng Li
  2. Leonidas J. Guibas
  3. Shaoshuai Shi
  4. Vladlen Koltun
  5. Or Litany
  6. Sai-Kit Yeung
  7. Binh-Son Hua
  8. Charles Ruizhongtai Qi

In Computational Mechanics

  1. Leonidas J. Guibas
  2. Or Litany
  3. Rohit Girdhar
  4. Ishan Misra
  5. Armand Joulin
  6. Charles Ruizhongtai Qi
  7. Matthias Nießner
  8. Chi-Wing Fu

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Xiaogang Wang
  4. Ming-Hsuan Yang
  5. Jitendra Malik
  6. Trevor Darrell
  7. Yi Yang
  8. Andrea Vedaldi

In Geology

  1. Or Litany
  2. Shaoshuai Shi
  3. Li Jiang
  4. Jiaya Jia
  5. Hongsheng Li
  6. Leonidas J. Guibas
  7. Charles Ruizhongtai Qi
  8. Rohit Girdhar

In Model Architectures

  1. Xiaogang Wang
  2. Jitendra Malik
  3. Chen Change Loy
  4. Ming-Ming Cheng
  5. Hongsheng Li
  6. Yu Qiao
  7. Dacheng Tao
  8. Jiaya Jia

In 3D Vision & Pose

  1. Leonidas J. Guibas
  2. Charles Ruizhongtai Qi
  3. Or Litany
  4. Sai-Kit Yeung
  5. Binh-Son Hua
  6. Michael M. Bronstein
  7. Rohit Girdhar
  8. M. Ovsjanikov

Citations in the corpus