Research map / 3D vision / Gaussian splatting
Triangle Splatting SLAM
Nicholas Fry, Eric Dexheimer, Kirill Mazur, Paul Kelly, Andrew Davison
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 depth supervision (ablation) | Triangle Splatting SLAM · TUM fr1/desk (ablation) | ATE (cm): 2.30 -> 1.77 | Improved |
| Add SSIM loss (ablation) | Triangle Splatting SLAM · TUM fr1/desk (ablation) | ATE (cm): 2.24 -> 1.77 | Improved |
| Add normal consistency loss (ablation) | Triangle Splatting SLAM · TUM fr1/desk (ablation) | ATE (cm): 1.82 -> 1.77 | Improved |
| Add equilateral regulariser (ablation) | Triangle Splatting SLAM · TUM fr1/desk (ablation) | ATE (cm) / PSNR: ATE 1.90 -> 1.77; PSNR 19.54 -> 18.87 | Mixed |
| Add densification (ablation) | Triangle Splatting SLAM · TUM (avg of 3 seqs, ablation) | ATE (cm): 1.94 -> 1.55 | Improved |
| Use mean vertex opacity instead of min opacity (ablation) | Triangle Splatting SLAM · TUM (avg of 3 seqs, ablation) | FPS: 1.33 -> 1.48 | Improved |
| Prune more non-opaque triangles (rho 0.4 vs 0.3) (ablation) | Triangle Splatting SLAM · TUM (avg of 3 seqs, ablation) | triangle count: 28k -> 48k | Hurt |
| Prune occluded triangles from Delaunay mesh (ablation) | Triangle Splatting SLAM · Replica (8 scenes) | Chamfer distance (cm): 1.55 -> 1.14 | Improved |
| Use triangle depth maps with TSDF vs MonoGS-2D* TSDF | Triangle Splatting SLAM · Replica (8 scenes) | Chamfer distance (cm): 1.36 -> 0.95 | Improved |
| Triangles vs MonoGS-2D* on tracking | Triangle Splatting SLAM · Replica (8 scenes) | ATE RMSE (cm): 0.24 -> 0.34 | Hurt |
| Triangle map vs MonoGS on photometric quality | Triangle Splatting SLAM · Replica (8 scenes) | PSNR: 38.94 -> 31.33 | 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.
- Co-SLAM — Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM (CVPR 2023) · better on 1 of 1 shared result
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 0.91)
- SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024 · similarity 0.89)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians (ICML 2025 · similarity 0.88)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.87)
- ActiveGAMER: Active GAussian Mapping through Efficient Rendering (CVPR 2025 · similarity 0.86)
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.
