In 3D reconstruction applications, an important issue is the matching of point clouds corresponding to different perspectives of a particular object or scene, which is addressed by the use of variants of the Iterative Closest Point (ICP) algorithm. In this work, we introduce a cloud-partitioning strategy for improved registration and compare it to other relevant approaches by using both time and quality of pose correction. Quality is assessed from a rotation metric and also by the root mean square error (RMSE) computed over the points of the source cloud and the corresponding closest ones in the corrected target point cloud. A wide and plural set of experimentation scenarios was used to test the algorithm and assess its generalization, revealing that our cloud-partitioning approach can provide a very good match in both indoor and outdoor scenes, even when the data suffer from noisy measurements or when the data size of the source and target models differ significantly. Furthermore, in most of the scenarios analyzed, registration with the proposed technique was achieved in shorter time than those from the literature.

This work presents an interpretable and privacy-aware solution for leakage detection in water distribution networks using federated prototype-based learning. Real data from pumping stations in Stockholm expose a non-independent and identically distributed data scenario, where each client reflects distinct operational conditions. Despite data heterogeneity, the model achieves consistently high performance. Interpretability is achieved via Voronoi-based prototypes, while privacy emerges from client-specific decision boundaries. The approach shows that combining federated learning and prototype-based models enables scalable, explainable, and secure anomaly detection in critical infrastructure.