Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
doc
 
 
 
 
 
 
 
 
 
 
 
 

Unpaired Point Cloud Completion on Real Scans using Adversarial Training

Implementation of ICLR 2020 paper (link).

Also check this! Our latest follow-up work published in ECCV 2020.

teaser

Dependencies

The code is tested with Python 3.5, TensorFlow 1.5, CUDA 9.0 on Ubuntu.

Installation

Compile Customized TF Operators from PointNet2

Instructions can be found from PointNet2.

Compile the EMD/Chamfer losses (CUDA implementations from Fan et al.)

cd pcl2pcl-gan-pub/pc2pc/structural_losses_utils
# with your editor, modify the paths in the makefile
make

Data

For convenience, we provide our synthetic clean and complete point clouds, and point representation data of 3D-EPN, download data with code: npaj. After download is finished, unzip the zip file, put it under pcl2pcl-gan-pub/pc2pc/data

Train

For training for a specific class (before that, cd pcl2pcl-gan-pub/pc2pc):

  1. train clean and complete AE: CUDA_VISIBLE_DEVICES=0 python3 train_ae_ShapeNet-v1.py

  2. train GAN: CUDA_VISIBLE_DEVICES=0 python3 train_pcl2pcl_gan_3D-EPN.py

Citation

@inproceedings{chen2020pcl2pcl,
  title={Unpaired Point Cloud Completion on Real Scans using Adversarial Training},
  author={Chen, Xuelin and Chen, Baoquan and Mitra, Niloy J},
  booktitle={Proceedings of the International Conference on Learning Representations (ICLR)},
  year={2020}
}

About

Unpaired Point Cloud Completion on Real Scans using Adversarial Training

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published