Geodesic-Based Bayesian Coherent Point Drift

Coherent point drift is a well-known algorithm for non-rigid registration, i.e., a procedure for deforming a shape to match another shape. Despite its prevalence, the algorithm has a major drawback that remains unsolved: It unnaturally deforms the different parts of a shape, e.g., human legs, when they are neighboring each other. The inappropriate deformations originate from a proximity-based deformation constraint, called motion coherence. This study proposes a non-rigid registration method that addresses the drawback. The key to solving the problem is to redefine the motion coherence using a geodesic, i.e., the shortest route between points on a shape's surface. We also propose the accelerated variant of the registration method. In numerical studies, we demonstrate that the algorithms can circumvent the drawback of coherent point drift. We also show that the accelerated algorithm can be applied to shapes comprising several millions of points.

A Novel Point Cloud Registration Method Based on ROPNet

Point cloud registration is a crucial preprocessing step for point cloud data analysis and applications. Nowadays, many deep-learning-based methods have been proposed to improve the registration quality. These methods always use the sum of two cross-entropy as a loss function to train the model, which may lead to mismatching in overlapping regions. In this paper, we designed a new loss function based on the cross-entropy and applied it to the ROPNet point cloud registration model. Meanwhile, we improved the ROPNet by adding the channel attention mechanism to make the network focus on both global and local important information, thus improving the registration performance and reducing the point cloud registration error. We tested our method on ModelNet40 dataset, and the experimental results demonstrate the effectiveness of our proposed method.