Corpus ID: 2271164

Generative and Discriminative Voxel Modeling with Convolutional Neural Networks

@article{Brock2016GenerativeAD,
  title={Generative and Discriminative Voxel Modeling with Convolutional Neural Networks},
  author={Andrew Brock and Theodore Lim and J. Ritchie and N. Weston},
  journal={ArXiv},
  year={2016},
  volume={abs/1608.04236}
}
When working with three-dimensional data, choice of representation is key. [...] Key Result 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.Expand
327 Citations
Image-to-Voxel Model Translation with Conditional Adversarial Networks
  • 17
  • PDF
Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in CNNs
  • 4
  • PDF
Equivariance for deep learning and retinal imaging
  • PDF
Occupancy Networks: Learning 3D Reconstruction in Function Space
  • 396
  • PDF
OPTIMIZATION USING VARIATIONAL AUTOENCODERS
  • 1
RocNet: Recursive Octree Network for Efficient 3D Deep Representation
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 27 REFERENCES
FusionNet: 3D Object Classification Using Multiple Data Representations
  • 151
  • Highly Influential
  • PDF
Identity Mappings in Deep Residual Networks
  • 4,544
  • PDF
A guide to convolution arithmetic for deep learning
  • 771
  • PDF
Procedural Modeling Using Autoencoder Networks
  • 52
  • PDF
Auto-Encoding Variational Bayes
  • 11,293
  • Highly Influential
  • PDF
3 D ShapeNets : A Deep Representation for Volumetric Shape Modeling
  • 67
  • Highly Influential
  • PDF
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
  • 21,987
  • Highly Influential
  • PDF
Orientation-boosted Voxel Nets for 3D Object Recognition
  • 150
  • Highly Influential
  • PDF
VoxNet: A 3D Convolutional Neural Network for real-time object recognition
  • Daniel Maturana, S. Scherer
  • Computer Science
  • 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2015
  • 1,571
  • Highly Influential
  • PDF
...
1
2
3
...