Self-Supervised Point Set Local Descriptors for Point Cloud Registration

  title={Self-Supervised Point Set Local Descriptors for Point Cloud Registration},
  author={Yijun Yuan and Jiawei Hou and A. N{\"u}chter and S. Schwertfeger},
  journal={Sensors (Basel, Switzerland)},
  • Yijun Yuan, Jiawei Hou, +1 author S. Schwertfeger
  • Published 2021
  • Computer Science, Medicine
  • Sensors (Basel, Switzerland)
  • Descriptors play an important role in point cloud registration. The current state-of-the-art resorts to the high regression capability of deep learning. However, recent deep learning-based descriptors require different levels of annotation and selection of patches, which make the model hard to migrate to new scenarios. In this work, we learn local registration descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one… CONTINUE READING
    1 Citations

    Figures, Tables, and Topics from this paper


    D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
    • 11
    • PDF
    MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds
    • 7
    • PDF
    3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
    • 298
    • Highly Influential
    • PDF
    3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
    • 91
    • Highly Influential
    • PDF
    RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor
    • 2
    • PDF
    The Perfect Match: 3D Point Cloud Matching With Smoothed Densities
    • 73
    • PDF
    PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
    • 3,499
    • Highly Influential
    • PDF
    PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
    • 2,227
    • PDF
    PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
    • 140
    • PDF