Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
Preprint
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
All Related Versions
This publication has 10 references indexed in Scilit:
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on LearningProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Orientation-boosted Voxel Nets for 3D Object Recognition2017
- Deep Networks with Stochastic Depth2016
- Identity Mappings in Deep Residual Networks2016
- Deep Residual Learning for Image Recognition2016
- Pairwise Decomposition of Image Sequences for Active Multi-view Recognition2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- Procedural Modeling Using Autoencoder Networks2015
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- 3D ShapeNets: A deep representation for volumetric shapes2015