It is the official code release of HEDNet (NeurIPS 2023) and SAFDNet (CVPR 2024). We implemented HEDNet and SAFDNet on all datasets based on OpenPCDet.
| Model | mAP/mAPH_L1 | mAP/mAPH_L2 | Vec_L1 | Vec_L2 | Ped_L1 | Ped_L2 | Cyc_L1 | Cyc_L2 |
|---|---|---|---|---|---|---|---|---|
| HEDNet-1x | 81.1/79.1 | 75.0/73.0 | 80.2/79.7 | 72.3/71.9 | 79.3/76.4 | 76.4/71.9 | 79.1/78.1 | 76.2/75.3 |
| SAFDNet-1x | 81.2/79.2 | 75.1/73.2 | 80.2/79.7 | 72.2/71.8 | 79.9/76.9 | 76.8/72.6 | 79.1/78.1 | 76.2/75.2 |
| HEDNet-2x | 81.4/79.5 | 75.3/73.4 | 81.1/80.6 | 73.2/72.7 | 84.4/80.0 | 76.8/72.6 | 78.7/77.7 | 75.8/74.9 |
| SAFDNet-2x | 81.8/79.9 | 75.7/73.9 | 80.6/80.1 | 72.7/72.3 | 84.7/80.4 | 77.3/73.1 | 80.0/79.0 | 77.2/76.2 |
| Model | mAP/mAPH_L1 | mAP/mAPH_L2 | Vec_L1 | Vec_L2 | Ped_L1 | Ped_L2 | Cyc_L1 | Cyc_L2 | Leaderboard |
|---|---|---|---|---|---|---|---|---|---|
| HEDNet-2x | 82.2/80.2 | 76.9/75.0 | 84.2/83.8 | 77.0/76.6 | 84.1/79.7 | 78.3/74.0 | 78.2/77.0 | 75.4/74.3 | link |
| SAFDNet-2x | 81.9/79.8 | 76.5/74.6 | 83.9/83.5 | 76.6/76.2 | 84.3/79.8 | 78.3/74.1 | 77.5/76.3 | 74.6/73.4 | Todo |
We could not provide the above pretrained models due to Waymo Dataset License Agreement.
| Model | mATE | mASE | mAOE | mAVE | mAAE | mAP | NDS | Checkpoint |
|---|---|---|---|---|---|---|---|---|
| HEDNet | 27.5 | 25.1 | 26.3 | 23.3 | 18.7 | 67.0 | 71.4 | Todo |
| SAFDNet | 27.2 | 25.1 | 24.9 | 25.6 | 18.9 | 66.3 | 71.0 | Todo |
| Model | mATE | mASE | mAOE | mAVE | mAAE | mAP | NDS | Leaderboard |
|---|---|---|---|---|---|---|---|---|
| HEDNet | 25.0 | 23.8 | 31.7 | 24.0 | 13.0 | 67.5 | 72.0 | json |
| SAFDNet | 25.1 | 24.2 | 31.1 | 25.8 | 12.7 | 68.3 | 72.3 | json |
| Model | mAP | Checkpoint |
|---|---|---|
| HEDNet-1x | 37.3 | Todo |
| SAFDNet-1x | 39.4 | Todo |
For OpenPCDet, please refer to INSTALL.md and GETTING_STARTED.md for the installation and usage, respectively. We used python 3.8, pytorch 1.10, cuda11.3, spconv-cu113 2.3.3. We provide a list of Python packages output from pip freeze here, to help configure the environment.
You can create an experiment folder in any location, and organize it like this:
FOLDER_NAME:
├── ${PATH_TO_HEDNet_ROOT}/HEDNet/tools/cfgs
├── ${PATH_TO_HEDNet_ROOT}/HEDNet/data
├── xxx.yaml (copy the yaml file here)
├── dist_train.sh (copy the training script from tools/scripts here)
├── dist_test.sh (copy the testing script from tools/scripts here)Then you can train and test models like this:
# Train with 8 gpus
./dist_train.sh xxx.yaml 8
# Test with 8 gpus
./dist_test.sh xxx.yaml 8 output/ckpt/xxx.pthHEDNet to get better results. We are trying to fix the gap and will update the code as soon as possible.@inproceedings{
zhang2023hednet,
title={{HEDNet}: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds},
author={Gang Zhang and Chen Junnan and Guohuan Gao and Jianmin Li and Xiaolin Hu},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
}
@misc{
zhang2024safdnet,
title={{SAFDNet}: A Simple and Effective Network for Fully Sparse 3D Object Detection},
author={Gang Zhang and Junnan Chen and Guohuan Gao and Jianmin Li and Si Liu and Xiaolin Hu},
year={2024},
eprint={2403.05817},
archivePrefix={arXiv},
primaryClass={cs.CV}
}This two works were supported by the National Key Research and Development Program of China (No. 2021ZD0200301) and the National Natural Science Foundation of China (Nos. U19B2034, 61836014) and THU-Bosch JCML center.