English

Generative and Discriminative Voxel Modeling with Convolutional Neural Networks

Computer Vision and Pattern Recognition 2016-08-17 v2 Human-Computer Interaction Machine Learning Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1608.04236,
  title  = {Generative and Discriminative Voxel Modeling with Convolutional Neural Networks},
  author = {Andrew Brock and Theodore Lim and J. M. Ritchie and Nick Weston},
  journal= {arXiv preprint arXiv:1608.04236},
  year   = {2016}
}

Comments

9 pages, 5 figures, 2 tables

R2 v1 2026-06-22T15:19:49.231Z