SPLATNet: Sparse Lattice Networks for Point Cloud Processing
Citations Over TimeTop 1% of 2018 papers
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. Naively applying convolutions on this lattice scales poorly, both in terms of memory and computational cost, as the size of the lattice increases. Instead, our network uses sparse bilateral convolutional layers as building blocks. These layers maintain efficiency by using indexing structures to apply convolutions only on occupied parts of the lattice, and allow flexible specifications of the lattice structure enabling hierarchical and spatially-aware feature learning, as well as joint 2D-3D reasoning. Both point-based and image-based representations can be easily incorporated in a network with such layers and the resulting model can be trained in an end-to-end manner. We present results on 3D segmentation tasks where our approach outperforms existing state-of-the-art techniques.
Related Papers
- → Analysis in indexing: document and domain centered approaches(2004)100 cited
- → A Review on Indexing Techniques and its application in Multilingual Information Retrieval System(2021)3 cited
- → Discussion on the Accurate Modeling of Cylindrical Indexing Cam(2013)
- The problems of Chinese Library Classification(CLC) in indexing of scientific and technical journals and the indexing principles(2008)
- A closer look on indexing and indexing parameters(2020)