Learning Adaptive Receptive Fields for Point Clouds

Xingtao Wang, Xiaopeng Fan, Yachun Wang

Abstract: Point cloud is an important type of geometric data structure. The uneven distribution of points brings challenges to the research of deep learning on point clouds. Many researchers are aware of this problem but have yet to come up with a specific solution. In this paper, we proposed a novel approach for learning receptive fields adapted to local point density variation and a density-targeted data augmentation strategy for point clouds. The receptive fields of the network can be adaptively adjusted by learning a weight matrix of local neighborhood points. Thus, our network is robust with respect to uneven distribution of points. Experiments show that methord in this paper achieves on par or better performance than state-of-the-art methods on multiple challenging benchmark datasets.