Structured-Li-GS integrates LiDAR-inertial-visual SLAM point clouds to initialize and constrain 3D Gaussians, using photometric, depth, normal, flattening, and offset losses to achieve high-quality results with fewer primitives and no densification.
arXiv preprint arXiv:2409.16296 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Tests linear, triangular, spline, MLS, Voronoi upsampling plus depth-guided lifting for better 3DGS on Mip-NeRF360 and Replica datasets, with scene-type guidelines.
citing papers explorer
-
Structured-Li-GS: Structured 3D Gaussians Splatting with LiDAR Incorporation and Spatial Constraints
Structured-Li-GS integrates LiDAR-inertial-visual SLAM point clouds to initialize and constrain 3D Gaussians, using photometric, depth, normal, flattening, and offset losses to achieve high-quality results with fewer primitives and no densification.
-
Optimizing 3D Gaussian Splatting via Point Cloud Upsampling
Tests linear, triangular, spline, MLS, Voronoi upsampling plus depth-guided lifting for better 3DGS on Mip-NeRF360 and Replica datasets, with scene-type guidelines.