SPLATNet: Sparse Lattice Networks for Point Cloud Processing

    CVPR, 2018.

    Cited by: 220|Bibtex|Views30|Links
    EI

    Abstract:

    We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. NaA¯vely applying convolutions on this lattice scales poorly, both in terms of memory and computational cost, as the size of the lattice increases. Instead, ou...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments