https://github.com/sky77764/pa-aug.pytorch

Part-Aware Data Augmentation for 3D Object Detection in Point Cloud (IROS 2021)
https://github.com/sky77764/pa-aug.pytorch

3d-object-detection data-augmentation lidar point-cloud

Last synced: 3 months ago
JSON representation

Part-Aware Data Augmentation for 3D Object Detection in Point Cloud (IROS 2021)

• Host: GitHub
• URL: https://github.com/sky77764/pa-aug.pytorch
• Owner: sky77764
• Created: 2020-09-01T06:45:35.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2022-10-23T05:38:25.000Z (about 2 years ago)
• Last Synced: 2023-11-28T08:42:00.858Z (12 months ago)
• Topics: 3d-object-detection, data-augmentation, lidar, point-cloud
• Language: Python
• Homepage:
• Size: 327 KB
• Stars: 69
• Watchers: 5
• Forks: 17
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Mixup - [Code

README

        
# Part-Aware Data Augmentation for 3D Object Detection in Point Cloud

This repository contains a reference implementation of our [Part-Aware Data Augmentation for 3D Object Detection in Point Cloud](https://ieeexplore.ieee.org/document/9635887) (IROS 2021).



  



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

```

@inproceedings{choi2021part,

  title={Part-aware data augmentation for 3d object detection in point cloud},

  author={Choi, Jaeseok and Song, Yeji and Kwak, Nojun},

  booktitle={2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},

  pages={3391--3397},

  year={2021},

  organization={IEEE}

}

```

## Prerequisites

Our code was tested on [second.pytorch](https://github.com/traveller59/second.pytorch) and [OpenPCDet](https://github.com/open-mmlab/OpenPCDet).  

This repository contains only part-aware data augmentation code.  

Refer to the link above for code such as data loader or detector.

## Usage

```

Args:

    ** only supports KITTI format **

    points: lidar points (N, 4), 

    gt_boxes: ground truth boxes (B, 7),

    gt_names: ground truth classes (B, 1), 

    class_names: list of classes to augment (3),

    pa_aug_param: parameters for PA_AUG (string).

Returns:

    points: augmented lidar points (N', 4),

    gt_boxes_mask: mask for gt_boxes (B)

class_names = ['Car', 'Pedestrian', 'Cyclist']

pa_aug_param = "dropout_p02_swap_p02_mix_p02_sparse40_p01_noise10_p01"

pa_aug = PartAwareAugmentation(points, gt_boxes, gt_names, class_names=class_names)

points, gt_boxes_mask = pa_aug.augment(pa_aug_param=pa_aug_param)

gt_boxes = gt_boxes[gt_boxes_mask]

```

## Example

Follow [this repo](https://github.com/sky77764/PA-AUG-MD3D) if you want to check the implementation on OpenPCDet.