3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
This addresses the problem of inefficient 3D semantic segmentation for applications using sparse data such as LiDAR or RGB-D cameras, representing a novel method for a known bottleneck.
The paper tackled the inefficiency of standard convolutional networks on sparse 3D data like point clouds by introducing submanifold sparse convolutional networks, which achieved state-of-the-art performance on a semantic segmentation competition test set.
Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard "dense" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and use them to develop spatially-sparse convolutional networks. We demonstrate the strong performance of the resulting models, called submanifold sparse convolutional networks (SSCNs), on two tasks involving semantic segmentation of 3D point clouds. In particular, our models outperform all prior state-of-the-art on the test set of a recent semantic segmentation competition.