Keywords
hierarchical spatial aggregation
point-cloud sparsity
paired simulation
reproducibility
Abstract
We evaluated hierarchical spatial aggregation for three-dimensional perception under 50% point-cloud sparsity. A deterministic paired simulation generated 64 cases and preserved a upper-severity quartile. Mean geometry recall changed from 0.522 to 0.563; the paired difference was +0.041 (95% interval +0.038 to +0.044). 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
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
Wang, L., Xu, Y., & Li, Y. (2017). Aerial Lidar Point Cloud Voxelization with its 3D Ground Filtering Application. Photogrammetric Engineering & Remote Sensing, 83(2), 95-107. https://doi.org/10.14358/pers.83.2.95
Vedashree Kedar Karandikar (2026). Camera-Based Depth Perception for Precision Agriculture: A Software-Defined Approach to 3D Scene Understanding. Journal of Information Systems Engineering and Management, 11(2s), 242-250. https://doi.org/10.52783/jisem.v11i2s.14375
Rezaei, S., Maier, A., & Arefi, H. (2024). Quality Analysis of 3D Point Cloud Using Low-Cost Spherical Camera for Underpass Mapping. Sensors, 24(11), 3534. https://doi.org/10.3390/s24113534
Altuntas, C. (2023). Review of Scanning and Pixel Array-Based LiDAR Point-Cloud Measurement Techniques to Capture 3D Shape or Motion. Applied Sciences, 13(11), 6488. https://doi.org/10.3390/app13116488
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
Fang, K., Xu, K., Wu, Z., Huang, T., & Yang, Y. (2023). Three-Dimensional Point Cloud Segmentation Algorithm Based on Depth Camera for Large Size Model Point Cloud Unsupervised Class Segmentation. Sensors, 24(1), 112. https://doi.org/10.3390/s24010112
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
Asafa, G. F., Ren, S., Mamun, S. S., & Gobena, K. A. (2025). DepthCloud2Point: Depth Maps and Initial Point for 3D Point Cloud Reconstruction from a Single Image. Electronics, 14(6), 1119. https://doi.org/10.3390/electronics14061119