Irregular Convolutional Auto-Encoder on Point Clouds
arXiv:1910.02686
Abstract
We proposed a novel graph convolutional neural network that could construct a coarse, sparse latent point cloud from a dense, raw point cloud. With a novel non-isotropic convolution operation defined on irregular geometries, the model then can reconstruct the original point cloud from this latent cloud with fine details. Furthermore, we proposed that it is even possible to perform particle simulation using the latent cloud encoded from some simulated particle cloud (e.g. fluids), to accelerate the particle simulation process. Our model has been tested on ShapeNetCore dataset for Auto-Encoding with a limited latent dimension and tested on a synthesis dataset for fluids simulation. We also compare the model with other state-of-the-art models, and several visualizations were done to intuitively understand the model.
20 pages, 7 figures
References in corpus (11)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Sequence to Sequence Learning with Neural Networks
- Conditional Generative Adversarial Nets
- Interaction Networks for Learning about Objects, Relations and Physics
- Layer Normalization
- Generative Moment Matching Networks
- Training generative neural networks via Maximum Mean Discrepancy optimization
- Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
- CycleGAN, a Master of Steganography
- Nonparametric Divergence Estimation with Applications to Machine Learning on Distributions
- Shape Generation using Spatially Partitioned Point Clouds