2021
Evaluating Initialization Methods for Discriminative and Fast-Converging HGMM Point Clouds
ICRA 2021poster
Discriminative data representations for point cloud data are critical for computer vision applications. Recently, the Hierarchical Gaussian Mixture Model (HGMM) has become a popular representation due to its compactness and real-time execution. However, HGMM still lacks a well-designed and robust in…