Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions


This repo contains the dataset and code for the paper Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions by Jiachen Sun et al. This codebase is based on SimpleView, and we thank the authors for their great contributions.



Download ModelNet40-C from Google Drive.

Download ModelNet40-C using our provided script.

Download ModelNet40-C from Zenodo.

ModelNet40-C Leaderboard

Architecture+Data Augmentation Leaderboard

Architecture Data Augmentation Corruption Error Rate Clean Error Rate Checkpoint
PCT PointCutMix-R 16.3 7.2 checkpoint
PCT PointCutMix-K 16.5 6.9 checkpoint
DGCNN PointCutMix-R 17.3 6.8 checkpoint
PCT RSMix 17.3 6.9 checkpoint
DGCNN PointCutMix-K 17.3 7.4 checkpoint
RSCNN PointCutMix-R 17.9 7.6 checkpoint
DGCNN RSMix 18.1 7.1 checkpoint
PCT PGD Adv Train 18.4 8.9 checkpoint
PointNet++ PointCutMix-R 19.1 7.1 checkpoint
PointNet++ PointMixup 19.3 7.1 checkpoint
PCT PointMixup 19.5 7.4 checkpoint
SimpleView PointCutMix-R 19.7 7.9 checkpoint
RSCNN PointMixup 19.8 7.2 checkpoint
PointNet++ PointCutMix-K 20.2 6.7 checkpoint

We allow users to directly download all pre-trained models with every data augmentation method here.

Architecture Leaderboard

Architecture Corruption Error Rate Clean Error Rate Checkpoint
PointNet++ 23.6 7.0 checkpoint
PCT 25.5 7.1 checkpoint
DGCNN 25.9 7.4 checkpoint
RSCNN 26.2 7.7 checkpoint
SimpleView 27.2 6.1 checkpoint
PointNet 28.3 9.3 checkpoint

More models’ results coming soon ……

We allow users to directly download all pre-trained models with standard training here.

Getting Started

First clone the repository. We would refer to the directory containing the code as ModelNet40-C.

git clone --recurse-submodules [email protected]:jiachens/ModelNet40-C.git


The code is tested on Linux OS with Python version 3.7.5, CUDA version 10.0, CuDNN version 7.6 and GCC version 5.4. We recommend using these versions especially for installing pointnet++ custom CUDA modules.

Install Libraries

We recommend you first install Anaconda and create a virtual environment.

conda create --name modelnetc python=3.7.5

Activate the virtual environment and install the libraries. Make sure you are in ModelNet40-C.

conda activate modelnetc
pip install -r requirements.txt
conda install sed  # for downloading data and pretrained models

For PointNet++, we need to install custom CUDA modules. Make sure you have access to a GPU during this step. You might need to set the appropriate TORCH_CUDA_ARCH_LIST environment variable depending on your GPU model. The following command should work for most cases export TORCH_CUDA_ARCH_LIST="6.0;6.1;6.2;7.0;7.5". However, if the install fails, check if TORCH_CUDA_ARCH_LIST is correctly set. More details could be found here.

Third-party modules pointnet2_pyt, PCT_Pytorch, emd, and PyGeM can be installed by the following script.


Download Datasets Including ModelNet40-C and Pre-trained Models

Make sure you are in ModelNet40-C. script can be used for downloading all the data and the pretrained models. It also places them at the correct locations.

To download ModelNet40 execute the following command. This will download the ModelNet40 point cloud dataset released with pointnet++ as well as the validation splits used in our work.

./ modelnet40

To generate the ModelNet40-C dataset, please run:

python data/

NOTE that the generation needs a monitor connected since Open3D library does not support background rendering.

We also allow users to download ModelNet40-C directly. Please fill this Google form while downloading our dataset.

./ modelnet40_c

To download the pretrained models with standard training recipe, execute the following command.

./ cor_exp

To download the pretrained models using different data augmentation strategies, execute the following command.

./ runs

New Features

  • We include Point Cloud Transformer (PCT) in our benchmark
  • ModelNet40-C/configs contains config files to enable different data augmentations and test-time adaptation methods
  • ModelNet40-C/ contains the data augmentation codes in our paper
  • ModelNet40-C/third_party contains the test-time adaptation used in our paper

Code Organization In Originial SimpleView

  • ModelNet40-C/models: Code for various models in PyTorch.
  • ModelNet40-C/configs: Configuration files for various models.
  • ModelNet40-C/ Training and testing any models.
  • ModelNet40-C/ Hyperparameters for different models and dataloader.
  • ModelNet40-C/ Code for different variants of the dataloader.
  • ModelNet40-C/* Code for various utility functions.

Running Experiments

Training and Config files

To train or test any model, we use the script. The format for running this script is as follows.

python --exp-config <path to the config>

The config files are named as <protocol>_<model_name><_extra>_run_<seed>.yaml (<protocol> ∈ [dgcnn, pointnet2, rscnn]; <model_name> ∈ [dgcnn, pointnet2, rscnn, pointnet, simpleview] ). For example, the config file to run an experiment for PointNet++ in DGCNN protocol with seed 1 dgcnn_pointnet2_run_1.yaml. To run a new experiment with a different seed, you need to change the SEED parameter in the config file. All of our experiments are done based on seed 1.

We additionally leverage PointCutMix: configs/cutmix, PointMixup: configs/mixup, RSMix: configs/rsmix, and PGD-based adversarial training configs/pgd as the training-time config files.

For example, to train PCT with PointCutMix-R, please use the following command:

python --exp-config configs/cutmix/pct_r.yaml

Evaluate a pretrained model

We provide pretrained models. They can be downloaded using the ./ cor_exp and ./ runs commands and are stored in the ModelNet40-C/runs (for data augmentation recipes) and ModelNet40-C/cor_exp (for standard trained models) folders. To test a pretrained model, the command is of the following format.

Additionally, we provide test-time config files in configs/bn and configs/tent for BN and TENT in our paper with the following commands:

python --entry test --model-path <cor_exp/runs>/<cfg_name>/<model_name>.pth --exp-config configs/<cfg_name>.yaml

We list all the evaluation commands in the,, scripts. Note that in it is expected that pgd with PointNet++, RSCNN, and SimpleView do not have outputs since they do not fit the adversarial training framework. We have mentioned this in our paper.


Please cite our paper and SimpleView if you use our benchmark and analysis results. Thank you!

      title={Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions}, 
      author={Jiachen Sun and Qingzhao Zhang and Bhavya Kailkhura and Zhiding Yu and Chaowei Xiao and Z. Morley Mao},
      journal={arXiv preprint arXiv:2201.12296},

  title={Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline},
  author={Goyal, Ankit and Law, Hei and Liu, Bowei and Newell, Alejandro and Deng, Jia},
  journal={International Conference on Machine Learning},


[1] Zhang, Jinlai, et al. “PointCutMix: Regularization Strategy for Point Cloud Classification.” arXiv preprint arXiv:2101.01461 (2021).

[2] Chen, Yunlu, et al. “Pointmixup: Augmentation for point clouds.” Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16. Springer International Publishing, 2020.

[3] Lee, Dogyoon, et al. “Regularization Strategy for Point Cloud via Rigidly Mixed Sample.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021.

[4] Sun, Jiachen, et al. “Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions.” Advances in Neural Information Processing Systems 34 (2021).

[5] Schneider, Steffen, et al. “Improving robustness against common corruptions by covariate shift adaptation.” arXiv preprint arXiv:2006.16971 (2020).

[6] Wang, Dequan, et al. “Tent: Fully test-time adaptation by entropy minimization.” arXiv preprint arXiv:2006.10726 (2020).

[7] Qi, Charles R., et al. “Pointnet: Deep learning on point sets for 3d classification and segmentation.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.

[8] Qi, Charles R., et al. “Pointnet++: Deep hierarchical feature learning on point sets in a metric space.” arXiv preprint arXiv:1706.02413 (2017).

[9] Liu, Yongcheng, et al. “Relation-shape convolutional neural network for point cloud analysis.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019.

[10] Wang, Yue, et al. “Dynamic graph cnn for learning on point clouds.” Acm Transactions On Graphics (tog) 38.5 (2019): 1-12.

[11] Goyal, Ankit, et al. “Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline.” arXiv preprint arXiv:2106.05304 (2021).

[12] Guo, Meng-Hao, et al. “Pct: Point cloud transformer.” Computational Visual Media 7.2 (2021): 187-199.