Need help with PF-Net-Point-Fractal-Network?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

132 Stars 37 Forks MIT License 60 Commits 20 Opened issues


CVPR2020 PF-Net: Point Fractal Network for 3D Point Cloud Completion

Services available


Need anything else?

Contributors list


This repository is still under constructions.

If you have any questions about the code, please email me. Thanks!

This is the Pytorch implement of CVPR2020 PF-Net: Point Fractal Network for 3D Point Cloud Completion.

0) Environment

Pytorch 1.0.1 Python 3.7.4

1) Dataset

  cd dataset
  You can also download the dataset from 
  链接: 提取码:3hoe 

2) Train


Change ‘croppointnum’ to control the number of missing points. Change ‘pointscaleslist ’to control different input resolutions. Change ‘D_choose’to control without using D-net.

3) Evaluate the Performance on ShapeNet


Show the completion results, the program will generate txt files in 'test-examples'.

Show the Chamfer Distances and two metrics in our paper.

4) Visualization of csv File

We provide some incomplete point cloud in file 'testone'. Use the following code to complete a incomplete point cloud of csv file: ``` python ``` change ‘infile’and ‘infilereal’to select different incomplete point cloud in ‘testone’

5) Visualization of Examples

Using Meshlab to visualize the txt files.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.