Generative and Discriminative Voxel Modeling with Convolutional Neural Networks

Andrew Brock, Theodore Lim, James Millar Ritchie, Nicholas J. Weston

Research output: Contribution to conferenceOtherpeer-review

217 Downloads (Pure)


When working with three-dimensional data, choice of representation is key. We
explore voxel-based models, and present evidence for the viability of voxellated
representations in applications including shape modeling and object classification. Our key contributions are methods for training voxel-based variational autoencoders, a user interface for exploring the latent space learned by the autoencoder, and a deep convolutional neural network architecture for object classification. We address challenges unique to voxel-based representations, and empirically evaluate our models on the ModelNet benchmark, where we demonstrate a 51.5% relative improvement in the state of the art for object classification.
Original languageEnglish
Number of pages9
Publication statusPublished - 5 Dec 2016
EventNeural Inofrmation Processing Conference: 3D Deep Learning - Barcelona, Barcelona, Spain
Duration: 5 Dec 201610 Dec 2016


ConferenceNeural Inofrmation Processing Conference
Abbreviated titleNIPS
Internet address


  • ModelNet benchmark
  • 3D Data
  • Convolutional Neural Networks
  • Variational Autoencoders


Dive into the research topics of 'Generative and Discriminative Voxel Modeling with Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this