Keywords
hierarchical spatial aggregation
point-cloud sparsity
paired simulation
reproducibility
Abstract
We evaluated hierarchical spatial aggregation for three-dimensional perception under 29% point-cloud sparsity. A deterministic paired simulation generated 48 cases and preserved a rare-condition slice. Mean geometry recall changed from 0.523 to 0.568; the paired difference was +0.045 (95% interval +0.043 to +0.047). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Sun, Y., Zia, A., Long, Z., Qiu, Z., Xiang, W., & Zhou, J. (2026). Hierarchical Spatial Mamba Framework for Point Cloud Classification. Lecture Notes in Computer Science, 402-417. https://doi.org/10.1007/978-981-95-4395-3_28
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
Yildiz, A. S., Meng, H., & Swash, M. R. (2025). Real-Time Object Detection and Distance Measurement Enhanced with Semantic 3D Depth Sensing Using Camera-LiDAR Fusion. Applied Sciences, 15(10), 5543. https://doi.org/10.3390/app15105543
Xiaoquan, L., & yang, Z. (2024). Depth-prior-based lidar point cloud de-noising method leveraging range-gated imaging. https://doi.org/10.1364/opticaopen.25909819.v1
Ortega, A., Silva, M., Teniente, E., Ferreira, R., Bernardino, A., Gaspar, J., & Andrade-Cetto, J. (2014). Calibration of an Outdoor Distributed Camera Network with a 3D Point Cloud. Sensors, 14(8), 13708-13729. https://doi.org/10.3390/s140813708
Zhang, L., Yu, X., Adu-Gyamfi, Y., & Sun, C. (2024). Spatio-Temporal Fusion of LiDAR and Camera Data for Omnidirectional Depth Perception. Transportation Research Record: Journal of the Transportation Research Board, 2678(4), 308-322. https://doi.org/10.1177/03611981231184187
Wu, D., Liang, Z., & Chen, G. (2022). Deep learning for LiDAR-only and LiDAR-fusion 3D perception: a survey. Intelligence & Robotics, 2(2), 105-129. https://doi.org/10.20517/ir.2021.20
Poliyapram, V., Wang, W., & Nakamura, R. (2019). A Point-Wise LiDAR and Image Multimodal Fusion Network (PMNet) for Aerial Point Cloud 3D Semantic Segmentation. Remote Sensing, 11(24), 2961. https://doi.org/10.3390/rs11242961
Gressin, A., Mallet, C., & David, N. (2012). IMPROVING 3D LIDAR POINT CLOUD REGISTRATION USING OPTIMAL NEIGHBORHOOD KNOWLEDGE. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, I-3, 111-116. https://doi.org/10.5194/isprsannals-i-3-111-2012
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