Update

Install

conda install pytorch==1.6.0 cudatoolkit=10.1 -c pytorch

Classification (ModelNet10/40)

Data Preparation

Run

# ModelNet40## Select different models in ./models## e.g., pointnet2_ssg without normal featurespython train_classification.py --model pointnet2_cls_ssg --log_dir pointnet2_cls_ssgpython test_classification.py --log_dir pointnet2_cls_ssg## e.g., pointnet2_ssg with normal featurespython train_classification.py --model pointnet2_cls_ssg --use_normals --log_dir pointnet2_cls_ssg_normalpython test_classification.py --use_normals --log_dir pointnet2_cls_ssg_normal## e.g., pointnet2_ssg with uniform samplingpython train_classification.py --model pointnet2_cls_ssg --use_uniform_sample --log_dir pointnet2_cls_ssg_fpspython test_classification.py --use_uniform_sample --log_dir pointnet2_cls_ssg_fps# ModelNet10## Similar setting like ModelNet40, just using --num_category 10## e.g., pointnet2_ssg without normal featurespython train_classification.py --model pointnet2_cls_ssg --log_dir pointnet2_cls_ssg --num_category 10python test_classification.py --log_dir pointnet2_cls_ssg --num_category 10

Performance

Part Segmentation (ShapeNet)

Data Preparation

Run

## Check model in ./models ## e.g., pointnet2_msgpython train_partseg.py --model pointnet2_part_seg_msg --normal --log_dir pointnet2_part_seg_msgpython test_partseg.py --normal --log_dir pointnet2_part_seg_msg

Performance

Semantic Segmentation (S3DIS)

Data Preparation

cd data_utilspython collect_indoor3d_data.py

Run

## Check model in ./models ## e.g., pointnet2_ssgpython train_semseg.py --model pointnet2_sem_seg --test_area 5 --log_dir pointnet2_sem_segpython test_semseg.py --log_dir pointnet2_sem_seg --test_area 5 --visual

Performance

Visualization

Using show3d_balls.py

## build C++ code for visualizationcd visualizerbash build.sh ## run one example python show3d_balls.py

Using MeshLab

Reference By

Citation

@article{Pytorch_Pointnet_Pointnet2,      Author = {Xu Yan},      Title = {Pointnet/Pointnet++ Pytorch},      Journal = {https://github.com/yanx27/Pointnet_Pointnet2_pytorch},      Year = {2019}}

@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}}

@InProceedings{yan20222dpass,      title={2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds},       author={Xu Yan and Jiantao Gao and Chaoda Zheng and Chao Zheng and Ruimao Zhang and Shuguang Cui and Zhen Li},      year={2022},      journal={ECCV}}

Selected Projects using This Codebase