Learning to Sample
Abstract
Processing large point clouds is a challenging task. Therefore, the data is often sampled to a size that can be processed more easily. The question is how to sample the data? A popular sampling technique is Farthest Point Sampling (FPS). However, FPS is agnostic to a downstream application (classification, retrieval, etc.). The underlying assumption seems to be that minimizing the farthest point distance, as done by FPS, is a good proxy to other objective functions. We show that it is better to learn how to sample. To do that, we propose a deep network to simplify 3D point clouds. The network, termed S-NET, takes a point cloud and produces a smaller point cloud that is optimized for a particular task. The simplified point cloud is not guaranteed to be a subset of the original point cloud. Therefore, we match it to a subset of the original points in a post-processing step. We contrast our approach with FPS by experimenting on two standard data sets and show significantly better results for a variety of applications. Our code is publicly available.
Cite
Text
Dovrat et al. "Learning to Sample." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00287Markdown
[Dovrat et al. "Learning to Sample." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/dovrat2019cvpr-learning/) doi:10.1109/CVPR.2019.00287BibTeX
@inproceedings{dovrat2019cvpr-learning,
title = {{Learning to Sample}},
author = {Dovrat, Oren and Lang, Itai and Avidan, Shai},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.00287},
url = {https://mlanthology.org/cvpr/2019/dovrat2019cvpr-learning/}
}