Three-dimensional (3D) building models with a high level of geometric and semantic detail are increasingly required to support fiscal cadastral applications, such as property valuation and taxation. In dense urban environments, however, the availability of complete and high-quality 3D data remains limited, particularly for exterior wall information. This research proposes a rule-based 3D building reconstruction workflow using integrated Unmanned Aerial Vehicle-Light-Detection and Ranging (UAV-LiDAR) and terrestrial handheld scanner point clouds to generate building models with hanging roofs and explicit building elements. The proposed method combines region growing segmentation for roof and exterior wall extraction, planar surface reconstruction through plane fitting, and geometric primitive intersection to construct roof meshes and building envelopes. Roof geometry is reconstructed from planar roof components, while exterior wall points are used to adjust the building envelope and support hanging roof modelling. The resulting 3D building model is represented as separated elements, including roof, exterior walls, and floor surfaces, enabling element-based area calculation and cost estimation for fiscal cadastral purposes. Quantitative evaluation using point cloud-to-model distance analysis shows that the reconstruction accuracy falls within the commonly reported range for Level of Detail 2 (LoD2) building models, despite limitations caused by segmentation precision and parameter sensitivity of rule-based algorithms. The results demonstrate that the proposed approach provides a feasible solution for 3D building modelling in environments with incomplete data, while supporting transparent and assessment-oriented fiscal cadastral workflows.