π CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection (NeurIPS2023)
π₯Please star CoDA β and share it. Thanksπ₯
[Paper] β [Project Page]
Yang Cao, Yihan Zeng, Hang Xu, Dan Xu
The Hong Kong University of Science and Technology
Huawei Noah's Ark Lab
π© Updates
β Latest papers&codes about open-vocabulary perception are collected here.
β All the codes, data and pretrained models have been released!
β The training and testing codes have been released.
β The pretrained models have been released.
β The OV-setting SUN-RGBD datasets have been released.
β The OV-setting ScanNet datasets have been released.
β Paper LaTeX codes are available at https://scienhub.com/Yang/CoDA.
Our code is based on PyTorch 1.8.1, torchvision==0.9.1, CUDA 10.1 and Python 3.7. It may work with other versions.
Please also install the following Python dependencies:
matplotlib
opencv-python
plyfile
'trimesh>=2.35.39,<2.35.40'
'networkx>=2.2,<2.3'
scipy
Please install pointnet2
layers by running
cd third_party/pointnet2 && python setup.py install
Please install a Cythonized implementation of gIOU for faster training.
conda install cython
cd utils && python cython_compile.py build_ext --inplace
To achieve the OV setting, we re-organize the original ScanNet and SUN RGB-D and adopt annotations of more categories. Please directly download the ov-setting datasets we provide here: OV SUN RGB-D and OV ScanNet.
Then run for the downloaded *.tar file:
mv sunrgbd_trainval.tar Data/sunrgb_d/
mv sunrgbd_v1_revised_0415.tar Data/sunrgb_d/
cd Data/sunrgb_d/
tar -xvf sunrgbd_v1_revised_0415.tar
tar -xvf sunrgbd_trainval.tar
cd -
mv scannet200_data.tar.* Data/scannet/
cd Data/scannet/
cat scannet200_data.tar.* | tar -xvf
cd -
Download the pretrained models here. Then run:
bash test_release_models.sh
bash scripts/coda_sunrgbd_stage1.sh
bash scripts/coda_sunrgbd_stage2.sh
If CoDA is helpful, please cite:
@inproceedings{cao2023coda,
title={CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection},
author={Cao, Yang and Zeng, Yihan and Xu, Hang and Xu, Dan},
booktitle={NeurIPS},
year={2023}
}
If you have any question or collaboration need (research purpose or commercial purpose), please email [email protected]
.
CoDA is inspired by CLIP and 3DETR. We appreciate their great codes.