Point Cloud Semantic Segmentation using Multi Scale Sparse Convolution Neural Network
This addresses the problem of limited multi-scale feature extraction in sparse point cloud segmentation for 3D scene understanding applications, representing an incremental improvement.
The authors tackled point cloud semantic segmentation by proposing a network with multi-scale sparse convolution and channel attention modules to capture richer feature information, achieving improved segmentation results on indoor (S3DIS) and outdoor (SemanticKITTI) datasets.
In recent years, with the development of computing resources and LiDAR, point cloud semantic segmentation has attracted many researchers. For the sparsity of point clouds, although there is already a way to deal with sparse convolution, multi-scale features are not considered. In this letter, we propose a feature extraction module based on multi-scale sparse convolution and a feature selection module based on channel attention and build a point cloud segmentation network framework based on this. By introducing multi-scale sparse convolution, the network could capture richer feature information based on convolution kernels with different sizes, improving the segmentation result of point cloud segmentation. Experimental results on Stanford large-scale 3-D Indoor Spaces(S3DIS) dataset and outdoor dataset(SemanticKITTI), demonstrate effectiveness and superiority of the proposed mothod.