Year: 2019
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Yuhui, Zhang, Gutmann, Greg, Akihiko, Konagaya
Institution: Tokyo Institute of Technology
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2977976628