Research map / 3D vision / Gaussian splatting
4D Gaussian Splatting SLAM
Yanyan Li, Youxu Fang, Zunjie Zhu, Kunyi Li, Yong Ding, Federico Tombari
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 separate static and dynamic Gaussians (ablation) | 4D-GS SLAM · BONN synchronous | PSNR: 18.37 -> 22.87 | Improved |
| add separate static and dynamic Gaussians (ablation) | 4D-GS SLAM · BONN synchronous2 | PSNR: 22.11 -> 24.84 | Improved |
| add optical flow loss when Gaussians are separated (ablation) | 4D-GS SLAM · BONN synchronous | PSNR: 22.87 -> 23.25 | Improved |
| add optical flow loss when Gaussians are separated (ablation) | 4D-GS SLAM · BONN synchronous2 | PSNR: 24.84 -> 25.42 | Improved |
| add optical flow loss without separating Gaussians (ablation) | 4D-GS SLAM · BONN synchronous | PSNR: 18.37 -> 17.40 | Hurt |
| add optical flow loss without separating Gaussians (ablation) | 4D-GS SLAM · BONN synchronous2 | PSNR: 22.11 -> 21.03 | Hurt |
| optimize first 3 window keyframes plus 2 random global and 5 overlapping keyframes with two-stage mapping (ablation) | 4D-GS SLAM · BONN/TUM mapping | rendering quality | Improved |
| model dynamic objects with 4D Gaussians instead of removing them, versus GS-SLAM baselines | 4D-GS SLAM · BONN | ATE RMSE: 33.1 -> 3.6 | Improved |
| use 4D-GS SLAM instead of SplaTAM | SLAM · TUM RGB-D dynamic | ATE RMSE: 62.2 -> 1.8 | Improved |
| use 4D-GS SLAM instead of SplaTAM | SLAM · BONN rendering | LPIPS: 0.233 -> 0.241 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SplaTAM — SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024) · better on 7 of 8 shared results
- SC-GS — SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (CVPR 2024) · 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
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.90)
- Gaussian Splatting SLAM (CVPR 2024 · similarity 0.90)
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · similarity 0.90)
- ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos (NeurIPS 2025 · similarity 0.89)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- Instant4D: 4D Gaussian Splatting in Minutes (NeurIPS 2025 · 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.
