Efficiency Evaluation of Sampling Density for Indoor Building LiDAR Point-Cloud Segmentation

Prior studies on indoor LiDAR point-cloud semantic segmentation consistently report that sampling density strongly affects segmentation accuracy as well as runtime and memory, establishing an accuracy-efficiency trade-off. Nevertheless, in practice, the density is often chosen heuristically and reported under heterogeneous protocols, which limits quantitative guidance. We present a unified evaluation framework that treats density as the sole independent variable. To control architectural variability, three representative backbones-PointNet, PointNet++, and DGCNN-are each augmented with an identical Point Transformer module, yielding PointNet-Trans, PointNet++-Trans, and DGCNN-Trans trained and tested under one standardized protocol. The framework couples isotropic voxel-guided uniform down-sampling with a decision rule integrating three signals: (i) accuracy sufficiency, (ii) the onset of diminishing efficiency, and (iii) the knee of the accuracy-density curve. Experiments on scan-derived indoor point clouds (with BIM-derived counterparts for contrast) quantify the accuracy-runtime trade-off and identify an engineering-feasible operating band of 1600-2900 points/m², with a robust setting near 2400 points/m². Planar components saturate at moderate densities, whereas beams are more sensitive to down-sampling. By isolating density effects and enforcing one protocol, the study provides reproducible, model-agnostic guidance for scan planning and compute budgeting in indoor mapping and Scan-to-BIM workflows.