LiDAR R-CNN: An Efficient and Universal 3D Object Detector
Introduction
This is the official code of LiDAR R-CNN: An Efficient and Universal 3D Object Detector. In this work, we present LiDAR R-CNN, a second stage detector that can generally improve any existing 3D detector. We find a common problem in Point-based RCNN, which is the learned features ignore the size of proposals, and propose several methods to remedy it. Evaluated on WOD benchmarks, our method significantly outperforms previous state-of-the-art.
中文介绍：https://zhuanlan.zhihu.com/p/359800738
Requirements
All the codes are tested in the following environment:
- Linux (tested on Ubuntu 16.04)
- Python 3.6+
- PyTorch 1.5 or higher (tested on PyTorch 1.5, 6, 7)
- CUDA 10.1
To install pybind11:
git clone [email protected]:pybind/pybind11.git
cd pybind11
mkdir build && cd build
cmake .. && make -j
sudo make install
To install requirements:
pip install -r requirements.txt
apt-get install ninja-build libeigen3-dev
Install LiDAR_RCNN library:
python setup.py develop --user
Preparing Data
Please refer to data processer to generate the proposal data.
Training
After preparing WOD data, we can train the vehicle only model in the paper, run this command:
python -m torch.distributed.launch --nproc_per_node=4 tools/train.py --cfg config/lidar_rcnn.yaml --name lidar_rcnn
For 3 class in WOD:
python -m torch.distributed.launch --nproc_per_node=8 tools/train.py --cfg config/lidar_rcnn_all_cls.yaml --name lidar_rcnn_all
The models and logs will be saved to work_dirs/outputs.
Evaluation
To evaluate, run distributed testing with 4 gpus:
python -m torch.distributed.launch --nproc_per_node=4 tools/test.py --cfg config/lidar_rcnn.yaml --checkpoint outputs/lidar_rcnn/checkpoint_lidar_rcnn_59.pth.tar
python tools/create_results.py --cfg config/lidar_rcnn.yaml
Note that, you should keep the nGPUS in config equal to nproc_per_node .This will generate a val.bin file in the work_dir/results. You can create submission to Waymo server using waymo-open-dataset code by following the instructions here.
Results
Our model achieves the following performance on:
Waymo Open Dataset Challenges (3D Detection)
| Proposals from | Class | Channel | 3D AP L1 Vehicle | 3D AP L1 Pedestrian | 3D AP L1 Cyclist |
|---|---|---|---|---|---|
| PointPillars | Vehicle | 1x | 75.6 | - | - |
| PointPillars | Vehicle | 2x | 75.6 | - | - |
| PointPillars | 3 Class | 1x | 73.4 | 70.7 | 67.4 |
| PointPillars | 3 Class | 2x | 73.8 | 71.9 | 69.4 |
| Proposals from | Class | Channel | 3D AP L2 Vehicle | 3D AP L2 Pedestrian | 3D AP L2 Cyclist |
|---|---|---|---|---|---|
| PointPillars | Vehicle | 1x | 66.8 | - | - |
| PointPillars | Vehicle | 2x | 67.9 | - | - |
| PointPillars | 3 Class | 1x | 64.8 | 62.4 | 64.8 |
| PointPillars | 3 Class | 2x | 65.1 | 63.5 | 66.8 |
Citation
If you find our paper or repository useful, please consider citing
@article{li2021lidar,
title={LiDAR R-CNN: An Efficient and Universal 3D Object Detector},
author={Li, Zhichao and Wang, Feng and Wang, Naiyan},
journal={CVPR},
year={2021},
}
1 Dec 19, 2021
164 Oct 30, 2022
35 Nov 26, 2022
23 Apr 06, 2022
21 Sep 30, 2022
1 Jan 10, 2022
1 Nov 05, 2021
304 Dec 28, 2022
1 Jun 12, 2022
0 Nov 12, 2021
39 Jan 01, 2023
1 Nov 05, 2022
32 Jan 03, 2023
3 May 19, 2022
25 Jul 27, 2022
11 Apr 18, 2022
126 Dec 06, 2022
16 Nov 29, 2022
3 Jan 10, 2022
2 Jul 01, 2022