Kernel-based feature aggregation framework in point cloud networks

Jianjia Zhang, Zhenxi Zhang, Lei Wang, Luping Zhou, Xiaocai Zhang, Mengting Liu, Weiwen Wu

Abstract: Highlights•We are among the first ones to investigate the drawbacks of maxpooling in deep point cloud networks. And based on our insightful analysis, a kernel-based feature aggregation framework is innovatively proposed for orderless point analysis via deep networks. The framework enables modeling nonlinear feature relationships which are complementary to max-pooling in a flexible manner.•The order-invariance property of max-pooling can be naturally kept by simply choosing an order-invariant kernel function, e.g., the commonly used RBF kernel or Polynomial kernel. At the same time, the high efficiency of max-pooling is also maintained and only very minor additional computational cost is introduced, which will be demonstrated later through theoretical analysis and experimental study.•The superiority and generability of the proposed method have been extensively verified in both supervised and unsupervised point cloud analysis tasks with various representative backbone networks. Specifically, the supervised tasks include 3D object classification, part segmentation, scene segmentation while the unsupervised task refers to place retrieval. The backbone networks involved in the evaluation include PointNet, DGCNN and PCT.