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

被引:13
|
作者
Zhang, Junming [1 ]
Yu, Ming-Yuan [1 ]
Vasudevan, Ram [1 ]
Johnson-Roberson, Matthew [1 ]
机构
[1] Univ Michigan, Ann Arbor, MI 48109 USA
关键词
D O I
10.1109/3DV50981.2020.00030
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
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.
引用
收藏
页码:200 / 209
页数:10
相关论文
共 50 条
  • [1] Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection
    Cheng, Gong
    Han, Junwei
    Zhou, Peicheng
    Xu, Dong
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (01) : 265 - 278
  • [2] Rotation-Invariant Gait Identification with Quaternion Convolutional Neural Networks
    Jing, Bowen
    Prabhu, Vinay
    Gu, Angela
    Whaley, John
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 15805 - 15806
  • [3] Rotation-invariant convolutional neural networks for galaxy morphology prediction
    Dieleman, Sander
    Willett, Kyle W.
    Dambre, Joni
    [J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2015, 450 (02) : 1441 - 1459
  • [4] Rotation-Invariant Wafer Map Pattern Classification With Convolutional Neural Networks
    Kang, Seokho
    [J]. IEEE ACCESS, 2020, 8 (08): : 170650 - 170658
  • [5] Multiscale Rotation-Invariant Convolutional Neural Networks for Lung Texture Classification
    Wang, Qiangchang
    Zheng, Yuanjie
    Yang, Gongping
    Jin, Weidong
    Chen, Xinjian
    Yin, Yilong
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2018, 22 (01) : 184 - 195
  • [6] SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation
    Sun, Xiao
    Lian, Zhouhui
    Xiao, Jianguo
    [J]. PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, : 980 - 988
  • [7] Investigation of the generalizing capabilities of convolutional neural networks in forming rotation-invariant attributes
    Malashin, R. O.
    Kadykov, A. B.
    [J]. JOURNAL OF OPTICAL TECHNOLOGY, 2015, 82 (08) : 509 - 515
  • [8] Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images
    Cheng, Gong
    Zhou, Peicheng
    Han, Junwei
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (12): : 7405 - 7415
  • [9] SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix
    Xu, Jianyun
    Tang, Xin
    Zhu, Yushi
    Sun, Jie
    Pu, Shiliang
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 10448 - 10457
  • [10] Rotation-Invariant Feature Learning via Convolutional Neural Network With Cyclic Polar Coordinates Convolutional Layer
    Mei, Shaohui
    Jiang, Ruoqiao
    Ma, Mingyang
    Song, Chao
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61