Research map / 3D vision / Gaussian splatting
Structure Gaussian Splatting SLAM
Yan Li, Yingzhao Li, Gim Hee Lee
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 planar Gaussian instances, structure closure and structure-aware optimization to MonoGS | MonoGS · Replica (8 seqs, avg) | PSNR (dB): 39.31 -> 39.70 | Improved |
| add structure closure and PGIs to MonoGS | MonoGS · Replica (8 seqs, avg ATE) | ATE RMSE (cm): 0.57 -> 0.22 | Improved |
| add structure closure and PGIs to MonoGS | MonoGS · TUM RGB-D (6 seqs, avg ATE) | ATE RMSE (cm): 2.34 -> 1.56 | Improved |
| add structure closure and PGIs to MonoGS | MonoGS · TUM fr3/notex_near (low texture) | ATE RMSE (cm): 55.59 -> 16.36 | Improved |
| replace loop closure (LoopSplat) with structure closure | LoopSplat · TUM fr3/notex_far (low texture) | ATE RMSE (cm): 8.18 -> 7.47 | Improved |
| reduce structure closure frequency from every 4 to every 25 frames (ablation) | structure closure · Replica R0 | ATE RMSE (cm): 0.32 -> 0.53 | Hurt |
| reduce structure closure frequency from every 4 to every 25 frames (ablation) | structure closure · Replica Off0 | ATE RMSE (cm): 0.25 -> 0.61 | Hurt |
| reduce structure closure frequency from every 4 to every 10 frames (ablation) | structure closure · Replica R0 | PSNR (dB): 36.59 -> 36.51 | No clear effect |
| use continuous color-embedding plane IDs instead of scalar plane ID (ablation) | PGI representation · Frame 0 plane learning (qualitative) | plane instance supervision | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- SplaTAM — SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024) · better on 3 of 3 shared results
- GS-SLAM — GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024) · better on 2 of 2 shared results
- Loopy-SLAM — Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024) · better on 2 of 2 shared results
- NICE-SLAM — NICE-SLAM: Neural Implicit Scalable Encoding for SLAM (CVPR 2022) · 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
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · similarity 0.93)
- SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embedding (ICCV 2025 · similarity 0.92)
- Gaussian Splatting SLAM (CVPR 2024 · similarity 0.92)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.90)
- VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians (ICML 2025 · similarity 0.90)
- SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024 · similarity 0.89)
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.
