Learning Efficient Rotation Representation for Point Cloud via Local-Global Aggregation
Lists
Only you see this
Abstract
Recently, there have been attempted to solve the problem of rotation perturbation in point cloud analysis. However, most of them fail to exploit the long-distance context and lose global location information. To address this issue, we propose a novel rotation-invariant network called LGANet, which is assembled with two key modules: local representation learning module and global alignment module. The local representation learning module is to capture local geometric features from K-nearest neighbors in both 3D Cartesian space and a latent space, while the global alignment module focuses on supplementing global location information with the adaptive selection mechanism. Extensive experiments on widely used datasets have demonstrated that our LGANet is superior to other state-of-the-art methods on the premise of ensuring rotation invariance in both classification and part segmentation.
BibTeX
@inproceedings{gu2021learning,
author = {Ruibin Gu and Qiuxia Wu and Hongbin Xu and Wing W. Y. Ng and Zhiyong Wang},
title = {{Learning Efficient Rotation Representation for Point Cloud via Local-Global Aggregation}},
booktitle = {ICME},
year = {2021},
doi = {10.1109/icme51207.2021.9428170},
}Loading related content...