Real-Aug

KO | EN

gitlite — search

#python #hacktoberfest #react #ai #typescript #android #machine-learning #deep-learning #nodejs #windows #kubernetes #awesome-list #security #pytorch

(★ 44)

Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection

Real-Aug Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

[![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://arxiv.org/abs/2305.12853)
# Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection
This is the official implementation of **Real-Aug**. 
In this work, we reveal the realisticness issue of vanilla synthesis-based LiDAR data augmentation and present a well-designed Real-Aug scheme. The proposed approaches are detector-agnostic and extra data-free. We hope that this work can draw more attention to the data aspect of 3D object detection.

For more details, please refer to: **Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection [[Paper](https://arxiv.org/abs/2305.12853)]** <br />
<p align="center"> <img src="img/real-aug.JPG" width="100%"> </p>

## News

## Citation 
If you find this project useful in your research, please consider citing:

```
@inproceedings{Real-Aug,
  title={Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection},
  author={Jinglin Zhan, Tiejun Liu, Rengang Li, Jingwei Zhang, Zhaoxiang Zhang, Yuntao Chen},
  journal = {arXiv preprint arXiv:2305.12853},
  year = 2023
}
```

## Acknowledgement
This work is built on  on the open-sourced [OpenPCDet](https://github.com/open-mmlab/OpenPCDet) and the published code of [CenterPoint](https://github.com/tianweiy/CenterPoint).

## License
This project is released under the [Apache 2.0 license](LICENSE).

Real-Aug

Real-Aug Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Real-Aug

Real-Aug Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README