PLS-GS: Probabilistic Lidar Scaffolds for Compact, Surface-Aligned Gaussian Splatting
PLS-GS: Probabilistic Lidar Scaffolds for Compact, Surface-Aligned Gaussian Splatting
This research introduces PLS-GS, a probabilistic LiDAR scaffold method for 3D Gaussian Splatting. By jointly fitting a Hierarchical Gaussian Mixture Model over position and color using both camera and LiDAR data, the approach constructs a continuous surface-aligned representation without discrete scene partitioning. Evaluated across five large outdoor scenes, PLS-GS places rendering primitives closer to LiDAR measurements than image- or LiDAR-initialized baselines while using substantially fewer primitives, resulting in a more compact model and faster rendering. The code is available at https://github.com/k-harikumar/PLS-GS.
The authors present PLS-GS, a method that integrates LiDAR data with Gaussian Splatting to create compact, surface-aligned 3D representations for robotics mapping tasks.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: Available Artifact link Open source S5
- paper: not_reported
- weights: not_reported
- dataset: not_reported
- code: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
the local surface frame induced by that component's covariance. A Mahalanobis support loss bounds the deviation of the rendering Gaussians from the corresponding LiDAR-derived surface. Across five large outdoor scenes, PLS-GS places primitives markedly closer to the LiDAR measurements than both image- and LiDAR-initialized baselines, while employing substantially fewer primitives, yielding a considerably more compac
Open source S4
t model and faster rendering. At matched capacity, PLS-GS places primitives closer to the LiDAR measurements, with comparable rendering quality. Code is available at https://github.com/k-harikumar/PLS-GS.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org