A Dynamical Perspective on Point Cloud Registration
We provide a dynamical perspective on the classical problem of 3D point cloud registration with correspondences. A point cloud is considered as a rigid body consisting of particles. The problem of registering two point clouds is formulated as a dynamical system, where the dynamic model point cloud translates and rotates in a viscous environment towards the static scene point cloud, under forces and torques induced by virtual springs placed between each pair of corresponding points. We first show that the potential energy of the system recovers the objective function of the maximum likelihood estimation. We then adopt Lyapunov analysis, particularly the invariant set theorem, to analyze the rigid body dynamics and show that the system globally asymptotically tends towards the set of equilibrium points, where the globally optimal registration solution lies in. We conjecture that, besides the globally optimal equilibrium point, the system has either three or infinite "spurious" equilibrium points, and these spurious equilibria are all locally unstable. The case of three spurious equilibria corresponds to generic shape of the point cloud, while the case of infinite spurious equilibria happens when the point cloud exhibits symmetry. Therefore, simulating the dynamics with random perturbations guarantees to obtain the globally optimal registration solution. Numerical experiments support our analysis and conjecture.
Code (0)
등록된 구현이 없습니다.
Tasks
Point Cloud RegistrationSimilar Papers 제목 키워드 기반
A Representation Separation Perspective to Correspondences-free Unsupervised 3D Point Cloud Registration
3D point cloud registration in remote sensing field has been greatly advanced by deep learning based methods, where the rigid transformation is either directly regressed from the two point clouds (correspondences-free ap…
Point Cloud RegistrationAPR: Online Distant Point Cloud Registration Through Aggregated Point Cloud Reconstruction
For many driving safety applications, it is of great importance to accurately register LiDAR point clouds generated on distant moving vehicles. However, such point clouds have extremely different point density and sensor…
Point cloud reconstructionPoint Cloud Registration3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds
Deep learning-based point cloud registration models are often generalized from extensive training over a large volume of data to learn the ability to predict the desired geometric transformation to register 3D point clou…
Meta-LearningPoint Cloud RegistrationColor Point Cloud Registration Based on Supervoxel Correspondence
With the development of RGBD sensors, the high-quality color point cloud can be obtained expediently. In this paper, we propose a novel registration method for 3D color point clouds from different views, which is a cri…
Point Cloud RegistrationSphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registration
Point cloud registration is to estimate a transformation to align point clouds collected in different perspectives. In learning-based point cloud registration, a robust descriptor is vital for high-accuracy registration.…
Point Cloud Registration