Learning Inner-Group Relations on Point Clouds
This work addresses the underexplored area of relation networks for point clouds, offering a scalable and efficient solution for computer vision applications, though it appears incremental as it builds on existing point-based methods.
The paper tackles the problem of learning relations within point groups for 3D point cloud tasks by proposing a group relation aggregator module and RPNet, achieving state-of-the-art results in classification and segmentation with around 30% parameter and 50% computation savings compared to PointNet++.
The prevalence of relation networks in computer vision is in stark contrast to underexplored point-based methods. In this paper, we explore the possibilities of local relation operators and survey their feasibility. We propose a scalable and efficient module, called group relation aggregator. The module computes a feature of a group based on the aggregation of the features of the inner-group points weighted by geometric relations and semantic relations. We adopt this module to design our RPNet. We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation. Surprisingly, empirical results show that wider RPNet fits for classification, while deeper RPNet works better on segmentation. RPNet achieves state-of-the-art for classification and segmentation on challenging benchmarks. We also compare our local aggregator with PointNet++, with around 30% parameters and 50% computation saving. Finally, we conduct experiments to reveal the robustness of RPNet with regard to rigid transformation and noises.