LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices

@article{Rosu2019LatticeNetFP,
  title={LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices},
  author={Radu Alexandru Rosu and Peer Schutt and Jan Quenzel and Sven Behnke},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.05905}
}
  • Radu Alexandru Rosu, Peer Schutt, +1 author Sven Behnke
  • Published 2019
  • Computer Science, Engineering, Mathematics
  • ArXiv
  • Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. However, applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of structured data. Here, we propose LatticeNet, a novel approach for 3D semantic segmentation, which takes as input raw point clouds. A PointNet describes the local geometry which we embed into a sparse permutohedral lattice. The lattice allows for fast… CONTINUE READING
    20 Citations

    Figures and Tables from this paper

    MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis
    • PDF
    LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment
    • PDF
    SalsaNext: Fast Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
    • 13
    Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation
    • 1
    • PDF
    3D Semantic Segmentation for Large-Scale Scene Understanding
    • 1
    • PDF
    Deep Learning for 3D Point Clouds: A Survey
    • 92
    • PDF
    SalsaNext: Fast, Uncertainty-Aware Semantic Segmentation of LiDAR Point Clouds
    • 13
    • PDF
    Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks
    • PDF
    AccSS3D: Accelerator for Spatially Sparse 3D DNNs
    • PDF

    References

    SHOWING 1-10 OF 44 REFERENCES
    SPLATNet: Sparse Lattice Networks for Point Cloud Processing
    • Hang Su, V. Jampani, +4 authors J. Kautz
    • Computer Science
    • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
    • 2018
    • 345
    • Highly Influential
    • PDF
    HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Clouds
    • 41
    • PDF
    PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
    • 3,520
    • Highly Influential
    • PDF
    3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
    • 282
    • PDF
    Tangent Convolutions for Dense Prediction in 3D
    • 171
    • PDF
    PointConv: Deep Convolutional Networks on 3D Point Clouds
    • 233
    • PDF
    SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
    • 134
    • PDF
    PointCNN: Convolution On X-Transformed Points
    • 524
    • PDF
    4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
    • 156
    • PDF
    Rethinking Atrous Convolution for Semantic Image Segmentation
    • 2,132
    • PDF