VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM
Not on the map. Why?
Abstract (arXiv)
We present VIGS-SLAM, a visual-inertial 3D Gaussian Splatting SLAM system that achieves robust real-time tracking and high-fidelity reconstruction. Although recent 3DGS-based SLAM methods achieve dense and photorealistic mapping, their purely visual design degrades under challenging conditions such as motion blur, low texture, and exposure variations. Our method tightly couples visual and inertial cues within a unified optimization framework, jointly optimizing camera poses, depths, and IMU states. It features robust IMU initialization, time-varying bias modeling, and loop closure with consistent Gaussian updates. Experiments on five challenging datasets demonstrate our superiority over state-of-the-art methods. Project page: https://vigs-slam.github.io
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 42 of its 75 references that are in the map. First posted on arXiv 2 Dec 2025.
Builds on
42 of 75 references.
References · 42
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
- 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
- 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
- 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
- 2016Direct Sparse Odometrycited by 485
- 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
- 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 423
- 2023Gaussian Splatting SLAMcited by 415
- 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
- 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
- 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
30 more
- 2023Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAMcited by 184
- 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 164
- 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
- 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 154
- 2023Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Camerascited by 141
- 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 129
- 2020TartanVO: A Generalizable Learning-based VOcited by 108
- 2024SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMcited by 87
- 2022Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mappingcited by 79
- 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 66
- 2023SNI-SLAM: Semantic Neural Implicit SLAMcited by 65
- 2024RGBD GS-ICP SLAMcited by 65
- 2024CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Fieldcited by 61
- 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 60
- 2025WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environmentscited by 50
- 2024FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometrycited by 44
- 2018Direct Sparse Visual-Inertial Odometry using Dynamic Marginalizationcited by 35
- 2023HI-SLAM: Monocular Real-time Dense Mapping with Hybrid Implicit Fieldscited by 31
- 2024HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstructioncited by 25
- 2023DNS SLAM: Dense Neural Semantic-Informed SLAMcited by 23
- 2024MM3DGS SLAM: Multi-modal 3D Gaussian Splatting for SLAM Using Vision, Depth, and Inertial Measurementscited by 22
- 2024NIS-SLAM: Neural Implicit Semantic RGB-D SLAM for 3D Consistent Scene Understandingcited by 19
- 2025GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splatscited by 14
- 2025VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenescited by 11
- 2022MeSLAM: Memory Efficient SLAM based on Neural Fieldscited by 10
- 2023NeRF-VINS: A Real-time Neural Radiance Field Map-based Visual-Inertial Navigation Systemcited by 7
- 2024DBA-Fusion: Tightly Integrating Deep Dense Visual Bundle Adjustment with Multiple Sensors for Large-Scale Localization and Mappingcited by 5
- 2025NeRF-VIO: Map-Based Visual-Inertial Odometry with Initialization Leveraging Neural Radiance Fieldscited by 3
- 2025GI-SLAM: Gaussian-Inertial SLAMcited by 2
- 2025MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mappingcited by 2
Built on by
Citing papers per year: 2026: 6.
6 papers.
- 2026Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directionscited by 2
- 2026Spectral GS-SLAM: Observability-Aware, Degeneracy-Robust Tracking for Real-Time 3D Gaussian Splatting SLAMcited by 1
- 2026GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decompositioncited by 0
- 2026DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstructioncited by 0
- 2026VI3: Grounding Pretrained 3D Foundation Models with Inertial Cuescited by 0
- 2026CLoSeR: Closing the Loop for Long-Context Streaming Reconstructioncited by 0
- 2026CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction1 Oct 2026
- 2026VI3: Grounding Pretrained 3D Foundation Models with Inertial Cues3 Sep 2026
- 2026DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstruction2 Aug 2026
- 2026GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition23 Jul 2026
- 2026Spectral GS-SLAM: Observability-Aware, Degeneracy-Robust Tracking for Real-Time 3D Gaussian Splatting SLAM19 Jun 2026
- 2026Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directions4 Feb 2026