VK-Net: Category-Level Point Cloud Registration with Unsupervised Rotation Invariant Keypoints
Lists
Only you see this
Abstract
In this paper, we propose VK-Net, a neural network that learns to discover a set of category-specific keypoints from a single point cloud in an unsupervised manner. VK-Net is able to generate semantically consistent and rotation invariant keypoints across objects of the same category and different views. Particularly, we find that utilizing learned keypoints for the task of point cloud registration outperforms other traditional and learning-based approaches. Given the paired source and target point clouds, we can construct keypoint correspondences from learned keypoints using VK-Net. These keypoint correspondences are then employed to calculate a good pose initialization, after which an ICP is utilized to refine the registration. Extensive experiments on the ShapeNet dataset demonstrate that our model outperforms the state-of-the-art methods by a large margin.
BibTeX
@inproceedings{chen2021vk,
author = {Zhi Chen and Wei Yang and Zhenbo Xu and Zhenbo Shi and Liusheng Huang},
title = {{VK-Net: Category-Level Point Cloud Registration with Unsupervised Rotation Invariant Keypoints}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2021},
url = {https://openreview.net/forum?id=0foiJwgqDV0},
}Loading related content...