SemiGMMPoint: Semi-supervised point cloud segmentation based on Gaussian mixture models

Xianwei Zhuang, Hualiang Wang, Xiaoxuan He, Siming Fu, Haoji Hu

Abstract: Highlights•Gaussian mixture-based generative classifiers improve point cloud segmentation.•Minimizing distribution similarity can improve the performance of GMM classifiers.•The sampling bias issue under 3D semi-supervised settings can be alleviated through GMM.•Combining Generative and contrastive methods fosters semi-supervised 3D segmentation.