Group-in-Group Relation-Based Transformer for 3D Point Cloud Learning

Deep point cloud neural networks have achieved promising performance in remote sensing applications, and the prevalence of Transformer in natural language processing and computer vision is in stark contrast to underexplored point-based methods. In this paper, we propose an effective transformer-based network for point cloud learning. To better learn global and local information, we propose a group-in-group relation-based transformer architecture to learn the relationships between point groups to model global information and between points within each group to model local semantic information. To further enhance the local feature representation, we propose a Radius Feature Abstraction (RFA) module to extract radius-based density features characterizing the sparsity of local point clouds. Extensive evaluation on public benchmark datasets demonstrate the effectiveness and competitive performance of our proposed method on point cloud classification and part segmentation.

Automated summary

In this paper, a transformer-based network for point cloud learning is proposed, which effectively models global and local information and enhances the feature representation through radius-based density features. Extensive evaluation demonstrates the effectiveness and competitive performance of the proposed method in point cloud classification and part segmentation.