Generative and Discriminative Voxel Modeling with Convolutional Neural Networks [article]

Andrew Brock, Theodore Lim, J.M. Ritchie, Nick Weston
2016 arXiv   pre-print
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
more » ... enges 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.
arXiv:1608.04236v2 fatcat:jurty7fbhbgwfazvjnsin46xk4