Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/orendv/learning_to_sample

A learned sampling approach for point clouds (CVPR 2019)
https://github.com/orendv/learning_to_sample

cvpr2019 deep-learning geometry-processing neural-network point-cloud sampling tensorflow

Last synced: 3 months ago
JSON representation

A learned sampling approach for point clouds (CVPR 2019)

Awesome Lists containing this project

README 

        
# Learning to Sample

Created by [Oren Dovrat*](https://www.linkedin.com/in/dovrat/), [Itai Lang*](https://itailang.github.io/), and [Shai Avidan](http://www.eng.tau.ac.il/~avidan/) from Tel-Aviv University. 


*Equal contribution



![teaser](./doc/teaser.png)



## Introduction

We propose a learned sampling approach for point clouds. Please see our [arXiv tech report](https://arxiv.org/abs/1812.01659) (or the [official CVPR 2019 version](https://openaccess.thecvf.com/content_CVPR_2019/html/Dovrat_Learning_to_Sample_CVPR_2019_paper.html)).



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](./doc/poster.png)



## 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"

* SampleNet: Differentiable Point Cloud Sampling by Lang *et al*. (CVPR 2020 Oral). This work extends "Learning to Sample" and proposes a novel differentiable relaxation for point cloud sampling.

* Multi-Stage Point Completion Network with Critical Set Supervision by Zhang *et al*. (submitted to CAGD; Special Issue of GMP 2020). This work evaluates our learned sampling as a supervision signal for point cloud completion network.

* MOPS-Net: A Matrix Optimization-driven Network for Task-Oriented 3D Point Cloud Downsampling by Qian *et al*. (arXiv  preprint). This work suggests an alternative network architecture for learned point cloud sampling. To train their network, the authors use our proposed losses for S-NET and ProgressiveNet.