This repository is for Dense-Resolution Networ (DRNet) introduced in the following paper
Shi Qiu Saeed Anwar, Nick Barnes
"Dense-Resolution Network for Point Cloud Classification and Segmentation"
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2021)
The paper can be downloaded from here (arXiv) or here (CVF), together with the supplementary material.
Download the ShapeNet Part Dataset and upzip it to your rootpath. Alternatively, you can modify the path of your dataset in cfgs/config_partseg_gpus.yaml
and cfgs/config_partseg_test.yaml
.
For PyTorch version <= 0.4.0, please refer to Relation-Shape-CNN.
For PyTorch version >= 1.0.0, please refer to Pointnet2_PyTorch.
Note:
In our DRNet, we use Farthest Point Sampling (e.g., pointnet2_utils.furthest_point_sample
) to down-sample the point cloud. Also, we adpot Feature Propagation (e.g., pointnet2_utils.three_nn
and pointnet2_utils.three_interpolate
) to up-sample the feature maps.
sh train_partseg_gpus.sh
Due to the complexity of DRNet, we support Multi-GPU via nn.DataParallel
. You can also adjust other parameters such as batch size or the number of input points in cfgs/config_partseg_gpus.yaml
, in order to fit the memory limit of your device.
You can set the path of your pre-trained model in cfgs/config_partseg_test.yaml
, then run:
sh voting_test.sh
If you find our paper is useful, please cite:
@inproceedings{qiu2021dense,
title={Dense-Resolution Network for Point Cloud Classification and Segmentation},
author={Qiu, Shi and Anwar, Saeed and Barnes, Nick},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month={January},
year={2021},
pages={3813-3822}
}
The code is built on Pointnet2_PyTorch, Relation-Shape-CNN, DGCNN. We thank the authors for sharing their codes.