SPLATNet: Sparse Lattice Networks for Point Cloud Processing

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.

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation ScanNet SPLAT Net test mIoU 39.3 # 29
3D Semantic Segmentation SemanticKITTI SPLATNet test mIoU 18.4% # 37
3D Part Segmentation ShapeNet-Part SPLATNet 3D Class Average IoU 82.0 # 32
Instance Average IoU 84.6 # 55

Methods


No methods listed for this paper. Add relevant methods here