OctNet: Learning Deep 3D Representations at High Resolutions

By Gernot Riegler, Ali O. Ulusoy, Andreas Geiger. 2016

1,618 citations recorded by the source corpus.

We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node stores a pooled feature representation. This allows to focus memory allocation and computation to the relevant dense regions and enables deeper networks without compromising resolution. We demonstrate the utility of our OctNet representation by analyzing the impact of resolution on several 3D tasks including 3D object classification, orientation estimation and point cloud labeling.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition, 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. Andreas Geiger
  2. Vladlen Koltun
  3. Jitendra Malik
  4. Matthias Nießner
  5. Leonidas J. Guibas
  6. Marc Pollefeys
  7. Charles Ruizhongtai Qi
  8. Angela Dai

In Computational Mechanics

  1. Andreas Geiger
  2. Leonidas J. Guibas
  3. Matthias Nießner
  4. Michael Niemeyer
  5. Jitendra Malik
  6. Yaron Lipman
  7. Binh-Son Hua
  8. Sai-Kit Yeung

In Computer Vision and Pattern Recognition

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

In Model Architectures

  1. Andreas Geiger
  2. Chunhua Shen
  3. Xiaogang Wang
  4. Raquel Urtasun
  5. Jitendra Malik
  6. Yu Qiao
  7. Silvio Savarese
  8. Vladlen Koltun

In 3D Vision & Pose

  1. Andreas Geiger
  2. Michael Niemeyer
  3. Jitendra Malik
  4. Matthias Nießner
  5. Justin Johnson
  6. Angela Dai
  7. Jiajun Wu
  8. Leonidas J. Guibas

Citations in the corpus