SPNet: Multi-Shell Kernel Convolution for Point Cloud Semantic Segmentation
This work addresses the problem of efficient and accurate semantic segmentation of large-scale point clouds for applications like autonomous driving or robotics, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles point cloud semantic segmentation by proposing SPConv, a novel convolution operator that splits 3D neighborhoods into shells and uses kernel points for local shape encoding, achieving top-ranking performances on large-scale datasets.
Feature encoding is essential for point cloud analysis. In this paper, we propose a novel point convolution operator named Shell Point Convolution (SPConv) for shape encoding and local context learning. Specifically, SPConv splits 3D neighborhood space into shells, aggregates local features on manually designed kernel points, and performs convolution on the shells. Moreover, SPConv incorporates a simple yet effective attention module that enhances local feature aggregation. Based upon SPConv, a deep neural network named SPNet is constructed to process large-scale point clouds. Poisson disk sampling and feature propagation are incorporated in SPNet for better efficiency and accuracy. We provided details of the shell design and conducted extensive experiments on challenging large-scale point cloud datasets. Experimental results show that SPConv is effective in local shape encoding, and our SPNet is able to achieve top-ranking performances in semantic segmentation tasks.