Home

Awesome

Learning to Sample

Created by Oren Dovrat*, Itai Lang*, and Shai Avidan from Tel-Aviv University. <br> *Equal contribution

teaser

Introduction

We propose a learned sampling approach for point clouds. Please see our arXiv tech report (or the official CVPR 2019 version).

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 generative deep network to simplify 3D point clouds. The network, termed S-NET, takes a point cloud and generates 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.

poster

Citation

If you find our work useful in your research, please consider citing:

@InProceedings{dovrat2019learning_to_sample,
  author = {Dovrat, Oren and Lang, Itai and Avidan, Shai},
  title = {{Learning to Sample}},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {2760--2769},
  year = {2019}
}

Installation and usage

This project contains two sub-directories, each is a stand-alone project with it's own instructions. Please see classification/README.md and reconstruction/README.md.

License

This project is licensed under the terms of the MIT license (see LICENSE for details).

Selected projects that use "Learning to Sample"