Interpolated Convolutional Networks for 3D Point Cloud Understanding

@article{Mao2019InterpolatedCN,
  title={Interpolated Convolutional Networks for 3D Point Cloud Understanding},
  author={Jiageng Mao and X. Wang and Hongsheng Li},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={1578-1587}
}
  • Jiageng Mao, X. Wang, Hongsheng Li
  • Published 2019
  • Computer Science, Engineering
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Point cloud is an important type of 3D representation. [...] Key Method A normalization term is introduced to handle neighborhoods of different sparsity levels. Our InterpConv is shown to be permutation and sparsity invariant, and can directly handle irregular inputs. We further design Interpolated Convolutional Neural Networks (InterpCNNs) based on InterpConv layers to handle point cloud recognition tasks including shape classification, object part segmentation and indoor scene semantic parsing. Experiments…Expand Abstract
    Local Grid Rendering Networks for 3D Object Detection in Point Clouds
    Learning to Segment 3D Point Clouds in 2D Image Space
    6
    Deep FusionNet for Point Cloud Semantic Segmentation
    Neural Implicit Embedding for Point Cloud Analysis
    Review: deep learning on 3D point clouds
    4
    Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation
    Pointwise Attention-Based Atrous Convolutional Neural Networks
    GRNet: Gridding Residual Network for Dense Point Cloud Completion
    1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 58 REFERENCES
    PointConv: Deep Convolutional Networks on 3D Point Clouds
    124
    PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
    2683
    Dynamic Graph CNN for Learning on Point Clouds
    676
    PointCNN: Convolution On X-Transformed Points
    328
    PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
    98
    Recurrent Slice Networks for 3D Segmentation of Point Clouds
    149
    Attentional ShapeContextNet for Point Cloud Recognition
    70
    PointCNN: convolution on Χ -transformed points
    206
    Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
    156