Research map / 3D vision / Gaussian splatting
Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping
Emanuele Giacomini, Luca Di Giammarino, Lorenzo De Rebotti, Giorgio Grisetti, Martin R. Oswald
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 |
|---|---|---|---|
| mesh from rendered range and normal maps with Poisson instead of marching cubes (ablation) | Splat-LOAM · quad-easy | F-score (%): 76.76 -> 96.74 | Improved |
| mesh from rendered range and normal maps instead of Poisson on Gaussian centers (ablation) | Splat-LOAM · quad-easy | F-score (%): 92.33 -> 96.74 | Improved |
| mesh from rendered maps instead of Poisson on centers (ablation) | Splat-LOAM · quad-easy | Chamfer-l1 (cm): 8.43 -> 5.37 | Improved |
| use joint geometric and photometric registration instead of point-to-point or point-to-plane (ablation) | Splat-LOAM odometry · quad-easy | RPE (%) | Improved |
| add photometric term to the geometric loss (ablation) | Splat-LOAM odometry · quad-easy | RPE (%) | Improved |
| increase active primitives from 200k to 300k (ablation) | Splat-LOAM mapping · campus | mapping FPS | No clear effect |
| use Splat-LOAM instead of OpenVDB | mapping · quad-easy | F-score (%): 88.85 -> 96.74 | Improved |
| use Splat-LOAM instead of PIN-SLAM | mapping · quad-easy | F-score (%): 88.05 -> 96.74 | Improved |
| use Splat-LOAM instead of N3-Mapping | mapping · observatory-01 | F-score (%): 87.94 -> 83.04 | Hurt |
| use Splat-LOAM instead of OpenVDB | mapping · keble-college02 | Chamfer-l1 (cm): 7.19 -> 7.43 | Mixed |
Later papers that compared with this method
1 later accepted paper reports Splat-LOAM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Real-Time LiDAR Gaussian Splatting SLAM via Geometry-Aware Covariance Coupling (ECCV 2026 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024 · similarity 0.90)
- Gaussian Splatting SLAM (CVPR 2024 · similarity 0.89)
- SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving (CVPR 2025 · similarity 0.89)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.88)
- D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction (NeurIPS 2025 · similarity 0.87)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · 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.
