Research map / 3D vision / Gaussian splatting
Real-Time LiDAR Gaussian Splatting SLAM via Geometry-Aware Covariance Coupling
SeungJun Tak, Yewon Jeon, Hwang Jaeik, Suk Min Hwang, SeongboHa SeongboHa, Hyeonwoo Yu
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 |
|---|---|---|---|
| initialize Gaussians from tracking covariances (rotation and scale) (ablation) | LiDAR GS-SLAM · Newer College quad | F-score (%): 48.688 -> 86.776 | Improved |
| add range-adaptive scale initialization (ablation) | LiDAR GS-SLAM · Oxford Spires Keble College | F-score (%): 51.582 -> 64.024 | Improved |
| add opacity initialization (ablation) | LiDAR GS-SLAM · Newer College quad | F-score (%): 86.020 -> 86.776 | Improved |
| add G-ICP normal term (ablation) | LiDAR GS-SLAM · Newer College quad | ATE RMSE (m): 0.099 -> 0.079 | Improved |
| add feature-aware map management (ablation) | LiDAR GS-SLAM · Newer College quad | F-score (%): 86.237 -> 86.776 | No clear effect |
| add GS map optimization feedback to tracking (ablation) | LiDAR GS-SLAM · Newer College quad | ATE RMSE (m): 0.099 -> 0.079 | Improved |
| add GS map optimization feedback to tracking (ablation) | LiDAR GS-SLAM · Newer College quad | Tracking FPS: 17.69 -> 23.70 | Improved |
| add scale regularization loss (ablation) | LiDAR GS-SLAM · Oxford Spires Keble College | F-score (%): 33.924 -> 64.024 | Improved |
| add opacity loss (ablation) | LiDAR GS-SLAM · Oxford Spires Keble College | F-score (%): 52.893 -> 64.024 | Improved |
| add planar cover and prune to opacity pruning (ablation) | LiDAR GS-SLAM · Newer College quad | #Gaussians: 239,175 -> 119,285 | Improved |
| add structure-aware splitting to opacity pruning (ablation) | LiDAR GS-SLAM · Newer College quad | F-score (%): 87.179 -> 88.040 | Improved |
| add structure-aware splitting to opacity pruning (ablation) | LiDAR GS-SLAM · Oxford Spires Keble College | F-score (%): 64.863 -> 56.681 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Splat-LOAM — Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping (ICCV 2025) · 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
- Gaussian Splatting SLAM (CVPR 2024 · similarity 0.90)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · similarity 0.90)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.89)
- D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction (NeurIPS 2025 · similarity 0.87)
- SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024 · similarity 0.87)
- 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.
