SD-Net: Symmetric-Aware Keypoint Prediction and Domain Adaptation for 6D Pose Estimation In Bin-picking Scenarios
This is the code of pytorch version for paper: [Symmetric-Aware Keypoint Prediction and Domain Adaptation for 6D Pose Estimation In Bin-picking Scenarios]
Illustration of the SD-Net architecture for 6DoF Pose Estimation in stacked scenarios.
We omit the domain adaptation framework, for brevity and more details can be found in :
.
Evaluation Siléane dataset
Evaluation Parametric dataset
Please clone the repository locally:
git clone https://github.com/TAO-TAO-TAO-TAO-TAO/SD-Net.git
Install the environment：
Install Pytorch. It is required that you have access to GPUs. The code is tested with Ubuntu 16.04/18.04, CUDA 10.0 and cuDNN v7.4, python3.6. Our backbone PointNet++ is borrowed from pointnet2. .Compile the CUDA layers for PointNet++, which we used in the backbone network:
cd tools\Sparepart\train.py
python train.py install
Install the following Python dependencies (with pip install):
matplotlib
opencv-python
plyfile
'trimesh>=2.35.39,<2.35.40'
'networkx>=2.2,<2.3'
torch==1.1.0
torchvision==0.3.0
sklearn
h5py
nibabel
cd tools\Sparepart\train.py
python train.py install
Dataset Siléane dataset is available at here. Parametric dataset is available at here. Fraunhofer IPA Bin-Picking dataset is available at here.
Evaluation metric The python code of evaluation metric is available at here.
If you find our work useful in your research, please consider citing:
@article{din2024SD-Net,
title={SD-Net: Symmetric-Aware Keypoint Prediction and Domain Adaptation for 6D Pose Estimation In Bin-picking Scenarios},
author={Ding-Tao Huang, En-Te Lin, Lipeng Chen2, Li-Fu Liu1, Long Zeng},
journal={arXiv preprint arXiv},
year={2024}
}
If you have any questions, please feel free to contact the authors.
Ding-Tao Huang: [email protected]
En-Te Lin: [email protected]
Li-Fu Liu: [email protected]