Keywords
hierarchical spatial aggregation
point-cloud sparsity
paired simulation
reproducibility
Abstract
We evaluated hierarchical spatial aggregation for three-dimensional perception under 19% point-cloud sparsity. A deterministic paired simulation generated 72 cases and preserved a median slice. Mean geometry recall changed from 0.582 to 0.630; the paired difference was +0.048 (95% interval +0.046 to +0.051). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
hou, B., Chen, Y., Long, Z., Wu, Y., & Chen, L. (2024). Falcon: Fused Attention for Lidar-Camera Curb Detection. . https://doi.org/10.2139/ssrn.5005833
Kitamoto, S., Hiroi, Y., Miyawaki, K., & Ito, A. (2025). Robust Human Tracking Using a 3D LiDAR and Point Cloud Projection for Human-Following Robots. Sensors, 25(6), 1754. https://doi.org/10.3390/s25061754
An, P., Ma, T., Yu, K., Fang, B., Zhang, J., Fu, W., & Ma, J. (2020). Geometric calibration for LiDAR-camera system fusing 3D-2D and 3D-3D point correspondences. Optics Express, 28(2), 2122. https://doi.org/10.1364/oe.381176
Wang, H., & Wang, S. (2018). Acquisition and Registration of Human Point Cloud Based on Depth Camera. MATEC Web of Conferences, 173, 03001. https://doi.org/10.1051/matecconf/201817303001
Kim, H., Yoon, W., & Kim, T. (2016). AUTOMATED MOSAICKING OF MULTIPLE 3D POINT CLOUDS GENERATED FROM A DEPTH CAMERA. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B3, 269-272. https://doi.org/10.5194/isprsarchives-xli-b3-269-2016
Jayaraj, P., & Ramiya, A. M. (2018). 3D CITYGML BUILDING MODELLING FROM LIDAR POINT CLOUD DATA. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-5, 175-180. https://doi.org/10.5194/isprs-archives-xlii-5-175-2018
Xie, Y., Fachada, S., Bonatto, D., Teratani, M., & Lafruit, G. (2021). View Synthesis: LiDAR Camera versus Depth Estimation. CSRN. https://doi.org/10.24132/csrn.2021.3101.35
Na, K. I., & Park, B. (2023). Real-time 3D multi-pedestrian detection and tracking using 3D LiDAR point cloud for mobile robot. ETRI Journal, 45(5), 836-846. https://doi.org/10.4218/etrij.2023-0116
Kulawiak, M. (2024). Comparison of 3D Point Cloud Completion Networks for High Altitude Lidar Scans of Buildings. Photogrammetric Engineering & Remote Sensing, 90(1), 55-64. https://doi.org/10.14358/pers.23-00056r2
Zhang, W., Qiu, W., Song, D., & Xie, B. (2019). Automatic Tunnel Steel Arches Extraction Algorithm Based on 3D LiDAR Point Cloud. Sensors, 19(18), 3972. https://doi.org/10.3390/s19183972