KPConv: Flexible and Deformable Convolution for Point Clouds

By Hugues Thomas, Charles Ruizhongtai Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui, François Goulette, Leonidas J. Guibas. 2019

3,358 citations recorded by the source corpus.

We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean space by kernel points, and applied to the input points close to them. Its capacity to use any number of kernel points gives KPConv more flexibility than fixed grid convolutions. Furthermore, these locations are continuous in space and can be learned by the network. Therefore, KPConv can be extended to deformable convolutions that learn to adapt kernel points to local geometry. Thanks to a regular subsampling strategy, KPConv is also efficient and robust to varying densities. Whether they use deformable KPConv for complex tasks, or rigid KPconv for simpler tasks, our networks outperform state-of-the-art classification and segmentation approaches on several datasets. We also offer ablation studies and visualizations to provide understanding of what has been learned by KPConv and to validate the descriptive power of deformable KPConv.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geology, 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 Computational Mechanics

  1. Or Litany
  2. Matthias Nießner
  3. Jiaya Jia
  4. Li Jiang
  5. Leonidas J. Guibas
  6. Shaoshuai Shi
  7. Vladlen Koltun
  8. Gerard Pons-Moll

In Computer Vision and Pattern Recognition

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

In Geology

  1. Or Litany
  2. Vladlen Koltun
  3. Matthias Nießner
  4. Li Jiang
  5. Shaoshuai Shi
  6. Jiaya Jia
  7. Angela Dai
  8. Xiaogang Wang

In 3D Vision & Pose

  1. Matthias Nießner
  2. Or Litany
  3. Angela Dai
  4. Andreas Geiger
  5. Marc Pollefeys
  6. Gerard Pons-Moll
  7. Jiajun Wu
  8. Silvio Savarese

Citations in the corpus