Contrastive Boundary Learning for Point Cloud Segmentation (CVPR 2022)

By Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, and Dacheng Tao

This is the implementation of our CVPR 2022 paper:
Contrastive Boundary Learning for Point Cloud Segmentation [arXiv]

cbl

If you find our work useful in your research, please consider citing:

@misc{tang2022contrastive,
    title={Contrastive Boundary Learning for Point Cloud Segmentation},
    author={Liyao Tang and Yibing Zhan and Zhe Chen and Baosheng Yu and Dacheng Tao},
    year={2022},
    eprint={2203.05272},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

Setup & Usage

For point-transformer baseline, please follow pytorch/README.

For ConvNet and other baselines, please follow tensorflow/README.

Pre-trained models

Pretrained models can be accessed here, together with training and testing log. Choose the desired baseline and unzip into the corresponding code directory (tensorflow/pytorch) and follow the README there for further instruction.

Quantitative results

S3DIS (Area 5)

baseline mIoU OA mACC
ConvNet + CBL 69.4 90.6 75.2
ConvNet + CBL (kl) 69.5 90.9 75.3
point-transformer + CBL 71.6 91.2 77.9

Qualitative results

demo

Acknowledgement

Codes are built based on a series of previous works, including:
KPConv,
RandLA-Net,
CloserLook3D,
Point-Transformer.
Thanks for their excellent work.

License

This repo is licensed under the terms of the MIT license (see LICENSE file for details).

GitHub

View Github