https://github.com/yangyanli/FPNN

Field Probing Neural Networks for 3D Data
https://github.com/yangyanli/FPNN

Last synced: 17 days ago
JSON representation

Field Probing Neural Networks for 3D Data

• Host: GitHub
• URL: https://github.com/yangyanli/FPNN
• Owner: yangyanli
• Created: 2016-03-20T11:50:39.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2018-03-01T04:52:44.000Z (over 6 years ago)
• Last Synced: 2024-08-01T03:29:07.247Z (3 months ago)
• Language: C++
• Homepage: https://arxiv.org/abs/1605.06240
• Size: 2.32 MB
• Stars: 54
• Watchers: 6
• Forks: 13
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# FPNN: Field Probing Neural Networks for 3D Data

Created by Yangyan Li, Soeren Pirk, Hao Su, Charles Ruizhongtai Qi, and Leonidas J. Guibas from Stanford University.

### Introduction

We propose a light-weight way for learning features from 3D data. See more details from our research paper on arXiv (was accepted to NIPS 2016).

### Usage

Check training settings for example usage of the field probing layers, as well as logs generated during our training.

### From FPNN to PointCNN

If you are interested in FPNN, we highly recommend you take a look at [PointCNN](https://github.com/yangyanli/PointCNN), which outperforms FPNN in terms of ModelNet40 classification, together with other advantages.