Research map / 3D vision / Gaussian splatting
VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM
Zihan Zhu, Wei Zhang, Moyang Li, Norbert Haala, Marc Pollefeys, Daniel Barath
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 IMU bias estimation (ablation) | VIGS-SLAM · EuRoC (stride = 10) | avg ATE RMSE (cm): 338.99 -> 3.39 | Improved |
| add IMU fusion to visual optimization (ablation) | VIGS-SLAM · EuRoC (stride = 10) | avg ATE RMSE (cm): 88.54 -> 3.39 | Improved |
| add three-stage IMU initialization (ablation) | VIGS-SLAM · EuRoC (stride = 10) | avg ATE RMSE (cm): 50.65 -> 3.39 | Improved |
| add IMU pre-integration keyframe pose initialization (ablation) | VIGS-SLAM · EuRoC (stride = 10) | avg ATE RMSE (cm): 40.94 -> 3.39 | Improved |
| add loop closure (ablation) | VIGS-SLAM · EuRoC (stride = 10) | avg ATE RMSE (cm): 23.78 -> 3.39 | Improved |
| use per-keyframe bias instead of one global bias (ablation) | VIGS-SLAM · EuRoC (stride = 10) | avg ATE RMSE (cm): 8.83 -> 3.39 | Improved |
| add IMU fusion to visual optimization (ablation) | VIGS-SLAM · EuRoC (stride = 10) | avg recall @10cm (%): 32.50 -> 98.99 | Improved |
| add loop closure (ablation) | VIGS-SLAM · EuRoC (stride = 10) | avg recall @10cm (%): 40.63 -> 98.99 | Improved |
| add loop closure Gaussian update (ablation) | VIGS-SLAM · FAST-LIVO2 rendering | PSNR: 22.06 -> 23.15 | Improved |
| add loop closure Gaussian update (ablation) | VIGS-SLAM · FAST-LIVO2 rendering | SSIM: 0.677 -> 0.729 | Improved |
| add loop closure Gaussian update (ablation) | VIGS-SLAM · FAST-LIVO2 rendering | LPIPS: 0.541 -> 0.487 | Improved |
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.
- DROID-SLAM — DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (NeurIPS 2021) · better on 3 of 3 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 0.93)
- Gaussian Splatting SLAM (CVPR 2024 · similarity 0.93)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · similarity 0.92)
- VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians (ICML 2025 · similarity 0.90)
- IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera (CVPR 2025 · similarity 0.90)
- WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments (CVPR 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.
