Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks

November 2020

Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks

Authors:

Junming Zhang, Ming-Yuan Yu, Ram Vasudevan, and M. Johnson-Roberson

Abstract:

Point cloud analysis is an area of increasing interest due to the development of 3D sensors that are able to rapidly measure the depth of scenes accurately. Unfortunately, applying deep learning techniques to perform point cloud analysis is non-trivial due to the inability of these methods to generalize to unseen rotations. To address this limitation, one usually has to augment the training data, which can lead to extra computation and require larger model complexity. This paper proposes a new neural network called the Aligned Edge Convolutional Neural Network (AECNN) that learns a feature representation of point clouds relative to Local Reference Frames (LRFs) to ensure invariance to rotation. In particular, features are learned locally and aligned with respect to the LRF of an automatically computed reference point. The proposed approach is evaluated on point cloud classification and part segmentation tasks. This paper illustrates that the proposed technique outperforms a variety of state of the art approaches (even those trained on augmented datasets) in terms of robustness to rotation without requiring any additional data augmentation.
@conference{Zhang-2020-130115,
author = {Junming Zhang And Ming-Yuan Yu And Ram Vasudevan And M. Johnson-Roberson},
title = {Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks},
booktitle = {Proceedings of International Conference on 3D Vision (3DV '20)},
year = {2020},
month = {November},
pages = {200 - 209},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.