PLS-GS: Probabilistic Lidar Scaffolds for Compact, Surface-Aligned Gaussian Splatting
Overview
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.
Generated from attributed reports · Updated 5 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Artifact availability · code: available
“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.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalPLS-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.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).