# OKVIS2: Realtime Scalable Visual-Inertial SLAM with Loop Closure

arXiv: https://arxiv.org/abs/2202.09199 · HTML: https://mlsanity.com/paper/2202.09199/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2022.

## Built on by (most cited first, 29 of 29)

- [GSFusion: Online RGB-D Mapping Where Gaussian Splatting Meets TSDF Fusion](https://mlsanity.com/paper/2408.12677/) (2024)
- [GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting](https://mlsanity.com/paper/2508.14717/) (2025)
- [Benchmarking Egocentric Visual-Inertial SLAM at City Scale](https://mlsanity.com/paper/2509.26639/) (2025)
- [NeRF-VO: Real-Time Sparse Visual Odometry with Neural Radiance Fields](https://mlsanity.com/paper/2312.13471/) (2023)
- [DVI-SLAM: A Dual Visual Inertial SLAM Network](https://mlsanity.com/paper/2309.13814/) (2023)
- [The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking](https://mlsanity.com/paper/2508.00088/) (2025)
- [FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment](https://mlsanity.com/paper/2504.08603/) (2025)
- [BodySLAM++: Fast and Tightly-Coupled Visual-Inertial Camera and Human Motion Tracking](https://mlsanity.com/paper/2309.01236/) (2023)
- [Incremental Dense Reconstruction from Monocular Video with Guided Sparse Feature Volume Fusion](https://mlsanity.com/paper/2305.14918/) (2023)
- [SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection for SLAM](https://mlsanity.com/paper/2504.00139/) (2025)
- [GloPro: Globally-Consistent Uncertainty-Aware 3D Human Pose Estimation & Tracking in the Wild](https://mlsanity.com/paper/2309.10369/) (2023)
- [Visual-Inertial Multi-Instance Dynamic SLAM with Object-level Relocalisation](https://mlsanity.com/paper/2208.04274/) (2022)
- [SOLVR: Submap Oriented LiDAR-Visual Re-Localisation](https://mlsanity.com/paper/2409.10247/) (2024)
- [VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion](https://mlsanity.com/paper/2607.27194/) (2026)
- [Landmark-based Localization using Stereo Vision and Deep Learning in GPS-Denied Battlefield Environment](https://mlsanity.com/paper/2402.12551/) (2024)
- [Addressing the challenges of loop detection in agricultural environments](https://mlsanity.com/paper/2408.15761/) (2024)
- [Holistic Fusion: Task- and Setup-Agnostic Robot Localization and State Estimation with Factor Graphs](https://mlsanity.com/paper/2504.06479/) (2025)
- [SMF-VO: Direct Ego-Motion Estimation via Sparse Motion Fields](https://mlsanity.com/paper/2511.09072/) (2025)
- [TAPFormer: Robust Arbitrary Point Tracking via Transient Asynchronous Fusion of Frames and Events](https://mlsanity.com/paper/2603.04989/) (2026)
- [An RTK-SLAM Dataset for Absolute Accuracy Evaluation in GNSS-Degraded Environments](https://mlsanity.com/paper/2604.07151/) (2026)
- [LAMP: Localization Aware Multi-camera People Tracking in Metric 3D World](https://mlsanity.com/paper/2605.05390/) (2026)
- [VOCA: Visual Odometry with Codec Awareness](https://mlsanity.com/paper/2607.00189/) (2026)
- [DynamicGlue: Epipolar and Time-Informed Data Association in Dynamic Environments using Graph Neural Networks](https://mlsanity.com/paper/2403.11370/) (2024)
- [E-S2Feat:Semantic-Guided Spiking Local Feature Detection and Description for Event Cameras](https://mlsanity.com/paper/2608.14027/) (2026)
- [SpotlessGS: Relightable 3D Gaussian Splatting under Dynamic Illumination for Robotic Perception](https://mlsanity.com/paper/2608.14713/) (2026)
- [CGS-SLAM: Collaborative Gaussian Splatting based SLAM for Multi-Agent Reconstruction](https://mlsanity.com/paper/2608.26868/) (2026)
- [CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction](https://mlsanity.com/paper/2610.01927/) (2026)
- [RoboCap: A New Platform for Egocentric Robot Learning](https://mlsanity.com/paper/2610.07217/) (2026)
- [RootSLAM: Square Root Bundle Adjustment for Visual-Inertial SLAM](https://mlsanity.com/paper/2610.15157/) (2026)

## Abstract (arXiv)

Robust and accurate state estimation remains a challenge in robotics, Augmented, and Virtual Reality (AR/VR), even as Visual-Inertial Simultaneous Localisation and Mapping (VI-SLAM) getting commoditised. Here, a full VI-SLAM system is introduced that particularly addresses challenges around long as well as repeated loop-closures. A series of experiments reveals that it achieves and in part outperforms what state-of-the-art open-source systems achieve. At the core of the algorithm sits the creation of pose-graph edges through marginalisation of common observations, which can fluidly be turned back into landmarks and observations upon loop-closure. The scheme contains a realtime estimator optimising a bounded-size factor graph consisting of observations, IMU pre-integral error terms, and pose-graph edges -- and it allows for optimisation of larger loops re-using the same factor-graph asynchronously when needed.