Home

Awesome

Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion (CVPR 2021)

PWC
PWC
PWC
PWC

This repository is for BAAF-Net introduced in the following paper:

"Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion"
Shi Qiu, Saeed Anwar, Nick Barnes
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)

Paper and Citation

The paper can be downloaded from here (CVF) or here (arXiv).
If you find our paper/codes/results are useful, please cite:

@inproceedings{qiu2021semantic,
  title={Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion},
  author={Qiu, Shi and Anwar, Saeed and Barnes, Nick},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages={1757-1767},
  year={2021}
}

Updates

Settings

Dataset

Training/Test

python -B main_S3DIS.py --gpu 0 --mode train --test_area 5

(Note: specify the --test_area from 1~6)

python -B main_S3DIS.py --gpu 0 --mode test --test_area 5 --model_path 'pretrained/Area5/snap-32251'

(Note: specify the --test_area index and the trained model path --model_path)

6-fold Cross Validation

Pretrained Models and Results on S3DIS Dataset

<p align="center"> <img width="1000" src="https://github.com/ShiQiu0419/BAAF-Net/blob/main/s3dis.png"> </p>

Results on SemanticKITTI Dataset

<p align="center"> <img width="1200" src="https://github.com/ShiQiu0419/BAAF-Net/blob/main/kitti_08.png"> </p>

Acknowledgment

The code is built on RandLA-Net. We thank the authors for sharing the codes.