A Multisource Heterogeneous Point Cloud Fine Registration Method for Large-Scale Outdoor Scenes

To provide a comprehensive representation of 3-D information in large-scale outdoor scenes, multiplatform, multisensor, and multitemporal laser point cloud acquisition and registration technologies have experienced rapid development. However, due to the complexity of outdoor environments and the differences in hardware performance across various observation platforms, significant challenges arise in accurately and efficiently registering multisource heterogeneous point clouds with inconsistent spatial coordinate systems. These challenges include substantial noise interference, occlusions, missing data, and geometric heterogeneity. In this article, we propose a heterogeneous point cloud fine registration method based on fully connected graph and heat conduction model. Specifically, we first establish initial correspondences for the classified feature primitives using a Gaussian probability distribution framework. Subsequently, low-level semantic association and rigid transformation compatibility check are employed to rapidly eliminate erroneous matching relationships caused by outliers. As a core step, we develop a homonymous point selection algorithm based on heat conduction simulation to accurately estimate robust correspondences for point cloud candidate pairs with limited overlap and discrete noise. The effectiveness of this approach is attributed to the similarity measure of spatial local geometric structures and global topological distributions provided by the nonlinear heat diffusion Laplacian matrix. Finally, a least-squares model weighted by a residual robust loss function is designed, incorporating facade information to solve for the optimal spatial transformation. Extensive experiments on multiple real-world datasets demonstrate that the proposed method inherits the effectiveness and robustness of geometry-based registration strategies, achieving precise fusion of edge positions in multisource heterogeneous point clouds, with an average root-mean-square error (RMSE) below 0.06 m. Compared to existing advanced registration methods (e.g., VGICP and Teaser++), the proposed method demonstrates outstanding registration performance and holds promising application prospects in fields such as fine-grained 3-D reconstruction.