dcp

by WangYueFt

WangYueFt /dcp
159 Stars 43 Forks Last release: Not found 5 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

Deep Closest Point

Prerequisites

PyTorch>=1.0: https://pytorch.org

scipy>=1.2

numpy

h5py

tqdm

TensorboardX: https://github.com/lanpa/tensorboardX

Training

DCP-v1

python main.py --expname=dcpv1 --model=dcp --emb_nn=dgcnn --pointer=identity --head=svd

DCP-v2

python main.py --expname=dcpv2 --model=dcp --emb_nn=dgcnn --pointer=transformer --head=svd

Testing

DCP-v1

python main.py --expname=dcpv1 --model=dcp --emb_nn=dgcnn --pointer=identity --head=svd --eval

or

python main.py --expname=dcpv1 --model=dcp --embnn=dgcnn --pointer=identity --head=svd --eval --modelpath=xx/yy

DCP-v2

python main.py --expname=dcpv2 --model=dcp --emb_nn=dgcnn --pointer=transformer --head=svd --eval

or

python main.py --expname=dcpv2 --model=dcp --embnn=dgcnn --pointer=transformer --head=svd --eval --modelpath=xx/yy

where xx/yy is the pretrained model

Citation

Please cite this paper if you want to use it in your work,

@InProceedings{Wang_2019_ICCV,
  title={Deep Closest Point: Learning Representations for Point Cloud Registration},
  author={Wang, Yue and Solomon, Justin M.},
  booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
  month = {October},
  year={2019}
}

License

MIT License

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.