Research map / 3D vision / Gaussian splatting
Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration
Kyoleen Kwak, Daeho Kim, Jeong Woon Lee, Hyoseok Hwang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add dense depth anchoring (DDA) (ablation) | Base · KITTI-360 | translation error E_t: 0.077 -> 0.068 | Improved |
| add dense depth anchoring (DDA) (ablation) | Base · KITTI-360 | rotation error E_r: 0.122 -> 0.117 | Improved |
| add gradient decoupling (GD) alone (ablation) | Base · KITTI-360 | translation error E_t: 0.077 -> 0.067 | Improved |
| add gradient decoupling (GD) alone (ablation) | Base · KITTI-360 | rotation error E_r: 0.122 -> 0.127 | Hurt |
| add GD on top of DDA (ablation) | DDA · KITTI-360 | translation error E_t: 0.068 -> 0.063 | Improved |
| add volumetric sparse masking (VSM) to DDA+GD (ablation) | GD+DDA · KITTI-360 | rotation error E_r: 0.124 -> 0.121 | Improved |
| add volumetric sparse masking (VSM) to DDA+GD (ablation) | GD+DDA · KITTI-360 | translation error E_t: 0.066 -> 0.063 | Improved |
| add DDA to Base (ablation) | Base · KITTI-360 | runtime: 875 -> 923 | Hurt |
| use GeoP-Calib vs HiGS-Calib | GeoP-Calib · KITTI-360 | translation error E_t: 0.103 -> 0.063 | Improved |
| use GeoP-Calib vs HiGS-Calib | GeoP-Calib · KITTI | translation error E_t: 0.055 -> 0.044 | Improved |
| use GeoP-Calib vs HiGS-Calib | GeoP-Calib · KITTI-360 | rotation error E_r: 0.140 -> 0.121 | Improved |
| use geometry preservation vs Base pipeline | GeoP-Calib · KITTI-360 | depth MAE: 0.294 -> 0.244 | Improved |
Closest papers by meaning
- A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds (ICCV 2025 · similarity 0.91)
- D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction (NeurIPS 2025 · similarity 0.91)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.88)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.88)
- SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving (CVPR 2025 · similarity 0.88)
- GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
