A framework that keeps 3D Gaussian Splatting geometry metric-accurate for LiDAR-camera calibration by using multi-view LiDAR depth supervision and blocking photometric updates to spatial parameters, outperforming prior targetless methods on driving datasets.
arXiv preprint arXiv:1803.08181 (2018)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration
A framework that keeps 3D Gaussian Splatting geometry metric-accurate for LiDAR-camera calibration by using multi-view LiDAR depth supervision and blocking photometric updates to spatial parameters, outperforming prior targetless methods on driving datasets.