MongeNet: Efficient Sampler for Geometric Deep Learning
Abstract
Recent advances in geometric deep-learning introduce complex computational challenges for evaluating the distance between meshes. From a mesh model, point clouds are necessary along with a robust distance metric to assess surface quality or as part of the loss function for training models. Current methods often rely on a uniform random mesh discretization, which yields irregular sampling and noisy distance estimation. In this paper we introduce MongeNet, a fast and optimal transport based sampler that allows for an accurate discretization of a mesh with better approximation properties. We compare our method to the ubiquitous random uniform sampling and show that the approximation error is almost half with a very small computational overhead.
Cite
Text
Lebrat et al. "MongeNet: Efficient Sampler for Geometric Deep Learning." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.01639Markdown
[Lebrat et al. "MongeNet: Efficient Sampler for Geometric Deep Learning." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/lebrat2021cvpr-mongenet/) doi:10.1109/CVPR46437.2021.01639BibTeX
@inproceedings{lebrat2021cvpr-mongenet,
title = {{MongeNet: Efficient Sampler for Geometric Deep Learning}},
author = {Lebrat, Leo and Cruz, Rodrigo Santa and Fookes, Clinton and Salvado, Olivier},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2021},
pages = {16664-16673},
doi = {10.1109/CVPR46437.2021.01639},
url = {https://mlanthology.org/cvpr/2021/lebrat2021cvpr-mongenet/}
}