Pytorch Implementation of PointNet and PointNet++

This repo is implementation for PointNet and PointNet++ in pytorch.

Update

2019/11/26:

(1) Fixed some errors in previous codes and added data augmentation tricks. Now classification by only 1024 points can achieve 92.8%!

(2) Added testing codes, including classification and segmentation, and semantic segmentation with visualization.

(3) Organized all models into ./models files for easy using.

If you find this repo useful in your research, please consider following and citing our other works:

@InProceedings{yan2020pointasnl,
  title={PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling},
  author={Yan, Xu and Zheng, Chaoda and Li, Zhen and Wang, Sheng and Cui, Shuguang},
  journal={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2020}
}

@InProceedings{yan2021sparse,
  title={Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion},
  author={Yan, Xu and Gao, Jiantao and Li, Jie and Zhang, Ruimao, and Li, Zhen and Huang, Rui and Cui, Shuguang},
  journal={AAAI Conference on Artificial Intelligence ({AAAI})},
  year={2021}
}

Classification

Data Preparation

Download alignment ModelNet here and save in data/modelnet40_normal_resampled/.

Run

## Check model in ./models 
## E.g. pointnet2_msg
python train_cls.py --model pointnet2_cls_msg --normal --log_dir pointnet2_cls_msg
python test_cls.py --normal --log_dir pointnet2_cls_msg

Performance

Part Segmentation

Data Preparation

Download alignment ShapeNet here and save in data/shapenetcore_partanno_segmentation_benchmark_v0_normal/.

Run

## Check model in ./models 
## E.g. pointnet2_msg
python train_partseg.py --model pointnet2_part_seg_msg --normal --log_dir pointnet2_part_seg_msg
python test_partseg.py --normal --log_dir pointnet2_part_seg_msg

Performance

Semantic Segmentation

Data Preparation

Download 3D indoor parsing dataset (S3DIS) here and save in data/Stanford3dDataset_v1.2_Aligned_Version/.

cd data_utils
python collect_indoor3d_data.py

Processed data will save in data/stanford_indoor3d/.

Run

## Check model in ./models 
## E.g. pointnet2_ssg
python train_semseg.py --model pointnet2_sem_seg --test_area 5 --log_dir pointnet2_sem_seg
python test_semseg.py --log_dir pointnet2_sem_seg --test_area 5 --visual

Visualization results will save in log/sem_seg/pointnet2_sem_seg/visual/ and you can visualize these .obj file by MeshLab.

Performance on sub-points of raw dataset (processed by official PointNet Link)

Performance on raw dataset

still on testing...

Visualization

Using show3d_balls.py

## build C++ code for visualization
cd visualizer
bash build.sh 
## run one example 
python show3d_balls.py

Using MeshLab

Reference By

halimacc/pointnet3
fxia22/pointnet.pytorch
charlesq34/PointNet
charlesq34/PointNet++

Environments

Ubuntu 16.04
Python 3.6.7
Pytorch 1.1.0