Problem
Research questions and friction points this paper is trying to address.
point cloud completion
3D reconstruction
LiDAR
glass windows
sparse sampling
A Three-Dimensional Reverse-Projection Method for Sparse Point Cloud Completion and Its Application to High-Speed Train Nose Reconstruction
🤖 AI Summary
This study addresses the point cloud missing and sparsity issues caused by LiDAR scanning through glass windows, constructing a complete non-contact digital modeling pipeline encompassing acquisition, filtering, completion, and surface reconstruction. Methodologically, it proposes a tri-axis back-projection completion algorithm that precisely fills voids through boundary identification and interpolation. Furthermore, it integrates FAST-LIVO2 localization, Moving Least Squares (MLS) smoothing, greedy triangulation, and Poisson surface reconstruction to achieve high-fidelity modeling. Experimental results demonstrate that the proposed method effectively recovers missing geometric information in glass regions, with reconstruction accuracy significantly outperforming existing approaches.
📝 Abstract
Holes in LiDAR scans of environments with glass windows remain an unresolved problem in three-dimensional reconstruction. This study presents a pipeline for point cloud acquisition, filtering, completion, and surface reconstruction to address sparse sampling and missing window regions in scans of a high-speed train nose. FAST-LIVO2 provides the initial point cloud through multisensor odometry and mapping, and moving least squares (MLS) smooths the observations. We then introduce three-axis projection-based subdivision and interpolation with reverse hole boundary identification, referred to as three-axis reverse completion. The method interpolates missing regions from observations around each hole. Greedy projection triangulation, Poisson surface reconstruction, and a Marching Cubes-based pipeline generate meshes from the completed point cloud. Experiments on a proportionally scaled display model of a high-speed train nose show that the proposed method fills missing point cloud regions around the glass windows. Under the evaluation setting used in this study, greedy projection triangulation yields lower geometric distance errors than the other two reconstruction pipelines. The pipeline supports non-contact digital modeling of train nose geometry and provides a practical approach to reconstructing objects with glass windows.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Point Cloud Completion
Reverse-Projection
Three-Axis Interpolation
3D Reconstruction
LiDAR
🔎 Similar Papers
No similar papers found.
