Keywords
hierarchical spatial aggregation
point-cloud sparsity
paired simulation
reproducibility
Abstract
We evaluated hierarchical spatial aggregation for three-dimensional perception under 45% point-cloud sparsity. A deterministic paired simulation generated 64 cases and preserved a median slice. Mean geometry recall changed from 0.558 to 0.602; the paired difference was +0.044 (95% interval +0.042 to +0.046). 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
Kim, M., Stoker, J., Irwin, J., Danielson, J., & Park, S. (2022). Absolute Accuracy Assessment of Lidar Point Cloud Using Amorphous Objects. Remote Sensing, 14(19), 4767. https://doi.org/10.3390/rs14194767
Ranasinghe, P., Patra, D., Banerjee, B., & Raval, S. (2025). LiDAR Point Cloud Colourisation Using Multi-Camera Fusion and Low-Light Image Enhancement. Sensors, 25(21), 6582. https://doi.org/10.3390/s25216582
Saksena, H., & Anwar, S. (2022). Fuzzy Logic Based Fusion of 2D LIDAR and Depth Camera Data for Robust Perception of Obstacle Distance. Volume 5: Dynamics, Vibration, and Control, V005T07A069. https://doi.org/10.1115/imece2022-95281
CANDAN, L., & KAÇAR, E. (2023). Methodology of real-time 3D point cloud mapping with UAV lidar. International Journal of Engineering and Geosciences, 8(3), 301-309. https://doi.org/10.26833/ijeg.1178260
Thielemann, J. T., & Thorstensen, J. (2025). 3D Point Cloud Verification and Scatter Removal Using a Dual Camera/Projector Setup. Sensors, 25(23), 7250. https://doi.org/10.3390/s25237250
He, C., Gong, J., Yang, Y., Bi, D., Lan, J., & Qie, L. (2021). Real-time Track Obstacle Detection from 3D LIDAR Point Cloud. Journal of Physics: Conference Series, 1910(1), 012002. https://doi.org/10.1088/1742-6596/1910/1/012002
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
Mi, G., Zhang, J., Li, J., & Zhuo, L. (2026). Hyper-source Enhanced Retrospective Attention Fusion for Camera-LiDAR 3D Object Detection. https://doi.org/10.2139/ssrn.6689267
Deng, W., Chen, X., & Jiang, J. (2024). A Staged Real-Time Ground Segmentation Algorithm of 3D LiDAR Point Cloud. Electronics, 13(5), 841. https://doi.org/10.3390/electronics13050841