Three-dimensional (3D) point clouds are important data representations in visualization applications. The rapidly growing utility and popularity of cloud processing strongly motivate a plethora research activities on large-scale feature extraction. In this work, we investigate resampling based hypergraph signal (HGSP). We develop novel method to extract sharp object features reduce the size rep...

Abstract Methods for processing point cloud information have seen a great success in collider physics applications. One recent breakthrough machine learning is the usage of transformer networks to learn semantic relationships between sequences language processing. In this work, we apply modified network called as method incorporate advantages architecture an unordered set particles resulting fr...

As 3D point cloud analysis has received increasing attention, the insufficient scale of datasets and weak generalization ability networks become prominent. In this paper, we propose a simple effective augmentation method for data to alleviate those problems. It finds one-to-one correspondence between two clouds generates new training by replacing points in one sample with their corresponding pa...

We propose the first fast and certifiable algorithm for registration of two sets three-dimensional (3-D) points in presence large amounts outlier correspondences. A certifiable algorithm is one that attempts to solve an intractable optimization problem (e.g., robust estimation with outliers) pr...