Probabilistic Point Cloud Modeling via Self-Organizing Gaussian Mixture Models
This addresses the challenge of balancing model fidelity and size for point cloud modeling, though it appears incremental as it builds on existing GMM methods with an adaptive twist.
The paper tackles the problem of probabilistic modeling for spatial point cloud data by introducing a self-organizing Gaussian Mixture Model that adapts its complexity based on scene information, evaluated against existing techniques on real-world data.
This letter presents a continuous probabilistic modeling methodology for spatial point cloud data using finite Gaussian Mixture Models (GMMs) where the number of components are adapted based on the scene complexity. Few hierarchical and adaptive methods have been proposed to address the challenge of balancing model fidelity with size. Instead, state-of-the-art mapping approaches require tuning parameters for specific use cases, but do not generalize across diverse environments. To address this gap, we utilize a self-organizing principle from information-theoretic learning to automatically adapt the complexity of the GMM model based on the relevant information in the sensor data. The approach is evaluated against existing point cloud modeling techniques on real-world data with varying degrees of scene complexity.