# Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration

arXiv: https://arxiv.org/abs/2606.20103 · HTML: https://mlsanity.com/paper/2606.20103/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image](https://mlsanity.com/paper/1812.00488/) (2018)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [Pixel-level Extrinsic Self Calibration of High Resolution LiDAR and Camera in Targetless Environments](https://mlsanity.com/paper/2103.01627/) (2021)
- [General, Single-shot, Target-less, and Automatic LiDAR-Camera Extrinsic Calibration Toolbox](https://mlsanity.com/paper/2302.05094/) (2023)
- [GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2403.11848/) (2024)
- [Automatic Extrinsic Calibration Method for LiDAR and Camera Sensor Setups](https://mlsanity.com/paper/2101.04431/) (2021)
- [OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving](https://mlsanity.com/paper/2205.14087/) (2022)
- [SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields](https://mlsanity.com/paper/2311.15803/) (2023)
- [3DGS-Calib: 3D Gaussian Splatting for Multimodal SpatioTemporal Calibration](https://mlsanity.com/paper/2403.11577/) (2024)
- [INF: Implicit Neural Fusion for LiDAR and Camera](https://mlsanity.com/paper/2308.14414/) (2023)
- [UniCal: Unified Neural Sensor Calibration](https://mlsanity.com/paper/2409.18953/) (2024)
- [Robust LiDAR-Camera Calibration with 2D Gaussian Splatting](https://mlsanity.com/paper/2504.00525/) (2025)
- [Targetless LiDAR-Camera Calibration with Neural Gaussian Splatting](https://mlsanity.com/paper/2504.04597/) (2025)
- [CLAIM: Camera-LiDAR Alignment with Intensity and Monodepth](https://mlsanity.com/paper/2512.14001/) (2025)

## Abstract (arXiv)

Accurate LiDAR-camera calibration is essential for robust multi-modal perception. Targetless approaches avoid manual setup but remain limited by the scarcity of discriminative cross-modal features. Recent methods address this by reconstructing the scene within a differentiable model, enabling extrinsic optimization through dense photometric supervision. Among these, 3D Gaussian Splatting (3DGS) has been widely adopted as a geometric proxy that bridges LiDAR and camera within a single differentiable framework. However, since 3DGS was originally designed for novel view synthesis, existing methods tend to prioritize rendering quality, causing the proxy geometry to drift from the true LiDAR structure. We propose a framework that preserves the metric geometry of the Gaussian proxy by aggregating multi-view LiDAR observations for dense depth supervision and blocking photometric gradients from updating the Gaussian spatial parameters. We validate our method on public driving datasets, where it consistently outperforms existing targetless methods in calibration accuracy.