Robust Rigid Point Registration based on Convolution of Adaptive Gaussian Mixture Models
This addresses the problem of reliable point cloud matching for applications in fields like robotics or computer vision, presenting a novel method for a known bottleneck.
The paper tackles robust and accurate 3D rigid point cloud registration in complex environments by proposing a new architecture that combines error estimation and dual global probability alignment using adaptive Gaussian Mixture Models (GMMs). The method demonstrates superior robustness and accuracy in thousands of trials on 200 models from public datasets, handling unpredictable noise, outliers, occlusion, and other challenges.
Matching 3D rigid point clouds in complex environments robustly and accurately is still a core technique used in many applications. This paper proposes a new architecture combining error estimation from sample covariances and dual global probability alignment based on the convolution of adaptive Gaussian Mixture Models (GMM) from point clouds. Firstly, a novel adaptive GMM is defined using probability distributions from the corresponding points. Then rigid point cloud alignment is performed by maximizing the global probability from the convolution of dual adaptive GMMs in the whole 2D or 3D space, which can be efficiently optimized and has a large zone of accurate convergence. Thousands of trials have been conducted on 200 models from public 2D and 3D datasets to demonstrate superior robustness and accuracy in complex environments with unpredictable noise, outliers, occlusion, initial rotation, shape and missing points.