/RPMNet

RPM-Net: Robust Point Matching using Learned Features (CVPR2020)

RPM-Net: Robust Point Matching using Learned Features

pic-network

This is the project webpage of our CVPR 2020 work. RPM-Net is a deep-learning approach designed for performing rigid partial-partial point cloud registration for objects in a iterative fashion. Our paper can be found on Arxiv.

@inproceedings{yew2020-RPMNet, 
    title={RPM-Net: Robust Point Matching using Learned Features}, 
    author={Yew, Zi Jian and Lee, Gim Hee}, 
    booktitle={Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2020} 
}

See the following link for a video demonstration of the results:

Source code

Will be released soon.