Awesome

:book: CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection (NeurIPS2023)

[Paper]   [Project Page] <br>

Yang Cao, Yihan Zeng, Hang Xu, Dan Xu <br> The Hong Kong University of Science and Technology<br> Huawei Noah's Ark Lab

:triangular_flag_on_post: Updates

☑ As the first work to introduce 3D Gaussian Splatting into 3D Object Detection, 3DGS-DET is released here !

☑ Our extended work CoDAv2 is released, check out it on arXiv !

☑ Latest papers&codes about open-vocabulary perception are collected here.

☑ All the codes, data and pretrained models have been released!

☑ The training and testing codes have been released.

☑ The pretrained models have been released.

☑ The OV-setting SUN-RGBD datasets have been released.

☑ The OV-setting ScanNet datasets have been released.

☑ Paper LaTeX codes are available at https://scienhub.com/Yang/CoDA.

Framework

Samples

Installation

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

Dataset preparation

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. You can also easily download them by running:

bash data_download.sh

Then run for the downloaded *.tar file:

bash data_preparation.sh

Evaluation

Download the pretrained models here. Then run:

bash test_release_models.sh

Training

bash scripts/coda_sunrgbd_stage1.sh
bash scripts/coda_sunrgbd_stage2.sh

Running Samples

bash run_samples.sh

:scroll: BibTeX

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}
}

@misc{cao2024collaborative,
      title={Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection}, 
      author={Yang Cao and Yihan Zeng and Hang Xu and Dan Xu},
      year={2024},
      eprint={2406.00830},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2406.00830}, 
}

:e-mail: Contact

If you have any question or collaboration need (research purpose or commercial purpose), please email yangcao.cs@gmail.com.

:scroll: Acknowledgement

CoDA is inspired by CLIP and 3DETR. We appreciate their great codes.