Corpus ID: 153312807

LSANet: Feature Learning on Point Sets by Local Spatial Attention

@article{Chen2019LSANetFL,
  title={LSANet: Feature Learning on Point Sets by Local Spatial Attention},
  author={Lin-Zhuo Chen and Xuan-yi Li and Deng-Ping Fan and Ming-Ming Cheng and K. Wang and Shao-Ping Lu},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.05442}
}
  • Lin-Zhuo Chen, Xuan-yi Li, +3 authors Shao-Ping Lu
  • Published 2019
  • Computer Science
  • ArXiv
  • Directly learning features from the point cloud has become an active research direction in 3D understanding. Existing learning-based methods usually construct local regions from the point cloud and extract the corresponding features using shared Multi-Layer Perceptron (MLP) and max pooling. However, most of these processes do not adequately take the spatial distribution of the point cloud into account, limiting the ability to perceive fine-grained patterns. We design a novel Local Spatial… CONTINUE READING
    RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
    • 42
    • PDF
    Deep Learning for 3D Point Clouds: A Survey
    • 37
    • PDF
    Are We Hungry for 3D LiDAR Data for Semantic Segmentation?
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 36 REFERENCES
    PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
    • 1,739
    • Highly Influential
    • PDF
    PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
    • 2,804
    • Highly Influential
    • PDF
    PointCNN: Convolution On X-Transformed Points
    • 348
    • Highly Influential
    • PDF
    PointCNN: convolution on Χ -transformed points
    • 212
    • Highly Influential
    Local Spectral Graph Convolution for Point Set Feature Learning
    • 90
    • PDF
    SPLATNet: Sparse Lattice Networks for Point Cloud Processing
    • 276
    • PDF
    Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs
    • 674
    • PDF
    Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks
    • 242
    • Highly Influential
    • PDF
    SO-Net: Self-Organizing Network for Point Cloud Analysis
    • 291
    • Highly Influential
    • PDF
    3D ShapeNets: A deep representation for volumetric shapes
    • 1,835
    • Highly Influential
    • PDF