NeiEA-NET: Semantic segmentation of large-scale point cloud scene via neighbor enhancement and aggregation

3D point cloud semantic segmentation is crucial for 3D environment perception and scene understanding, where learning of local context in point clouds is a crucial challenge. Existing approaches typically explore local context based on the predefined neighbors of point clouds. However, the widely used K-nearest neighbor algorithm (KNN) is far from optimal in defining local neighbors. In this study, we propose NeiEA-Net, a conceptually simple and effective network for point cloud semantic segmentation. The key to our approach is to optimize the local neighbors in 3D Euclidean space by taking full advantage of high-dimensional feature space as much as possible. In addition, we introduce a neighbor feature aggregation module to adaptively aggregate features with different scales in the local neighbors to further reduce the redundant information, thereby effectively learning the local details of point clouds. Experiments conducted on three large-scale benchmarks, S3DIS, Toronto3D and SensatUrban, demonstrate the superiority of our network.

Automated summary

3D point cloud semantic segmentation is crucial for understanding 3D environments. Existing approaches of local context learning in point clouds are based on predefined neighbors, but K-nearest neighbor algorithm (KNN) is suboptimal. This study proposes NeiEA-Net, a simple and effective network that optimizes local neighbors in high-dimensional feature space for semantic segmentation of point clouds. The network further reduces redundant information by adaptively aggregating features of different scales. Experimental results on three large-scale benchmarks demonstrate the superiority of this network.