# DM-VIO: Delayed Marginalization Visual-Inertial Odometry

arXiv: https://arxiv.org/abs/2201.04114 · HTML: https://mlsanity.com/paper/2201.04114/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 11 Jan 2022.

## Builds on (most cited first, 11 of 11)

- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping](https://mlsanity.com/paper/1910.02490/) (2019)
- [The TUM VI Benchmark for Evaluating Visual-Inertial Odometry](https://mlsanity.com/paper/1804.06120/) (2018)
- [4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving](https://mlsanity.com/paper/2009.06364/) (2020)
- [Visual-Inertial Mapping with Non-Linear Factor Recovery](https://mlsanity.com/paper/1904.06504/) (2019)
- [Direct Sparse Visual-Inertial Odometry using Dynamic Marginalization](https://mlsanity.com/paper/1804.05625/) (2018)
- [Visual-Inertial Monocular SLAM with Map Reuse](https://mlsanity.com/paper/1610.05949/) (2016)
- [Inertial-Only Optimization for Visual-Inertial Initialization](https://mlsanity.com/paper/2003.05766/) (2020)

## Built on by (most cited first, 23 of 23)

- [Deep Event Visual Odometry](https://mlsanity.com/paper/2312.09800/) (2023)
- [Benchmarking Egocentric Visual-Inertial SLAM at City Scale](https://mlsanity.com/paper/2509.26639/) (2025)
- [4DRVO-Net: Deep 4D Radar-Visual Odometry Using Multi-Modal and Multi-Scale Adaptive Fusion](https://mlsanity.com/paper/2308.06573/) (2023)
- [RD-VIO: Robust Visual-Inertial Odometry for Mobile Augmented Reality in Dynamic Environments](https://mlsanity.com/paper/2310.15072/) (2023)
- [The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking](https://mlsanity.com/paper/2508.00088/) (2025)
- [DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment](https://mlsanity.com/paper/2209.14965/) (2022)
- [Tight Fusion of Events and Inertial Measurements for Direct Velocity Estimation](https://mlsanity.com/paper/2401.09296/) (2024)
- [Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction](https://mlsanity.com/paper/2504.13419/) (2025)
- [MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM](https://mlsanity.com/paper/2509.20757/) (2025)
- [4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions](https://mlsanity.com/paper/2301.01147/) (2022)
- [SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System](https://mlsanity.com/paper/2312.01616/) (2023)
- [DBA-Fusion: Tightly Integrating Deep Dense Visual Bundle Adjustment with Multiple Sensors for Large-Scale Localization and Mapping](https://mlsanity.com/paper/2403.13714/) (2024)
- [Causal Transformer for Fusion and Pose Estimation in Deep Visual Inertial Odometry](https://mlsanity.com/paper/2409.08769/) (2024)
- [High-Speed Stereo Visual SLAM for Low-Powered Computing Devices](https://mlsanity.com/paper/2410.04090/) (2024)
- [BS3D: Building-scale 3D Reconstruction from RGB-D Images](https://mlsanity.com/paper/2301.01057/) (2023)
- [Discovering Multiple Algorithm Configurations](https://mlsanity.com/paper/2303.07434/) (2023)
- [A Plug-and-Play Learning-based IMU Bias Factor for Robust Visual-Inertial Odometry](https://mlsanity.com/paper/2503.12527/) (2025)
- [VOCA: Visual Odometry with Codec Awareness](https://mlsanity.com/paper/2607.00189/) (2026)
- [Universal Online Temporal Calibration for Optimization-based Visual-Inertial Navigation Systems](https://mlsanity.com/paper/2501.01788/) (2025)
- [Edge-Enabled VIO with Long-Tracked Features for High-Accuracy Low-Altitude IoT Navigation](https://mlsanity.com/paper/2505.06517/) (2025)
- [Dual-Agent Reinforcement Learning for Adaptive and Cost-Aware Visual-Inertial Odometry](https://mlsanity.com/paper/2511.21083/) (2025)
- [PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment](https://mlsanity.com/paper/2607.00176/) (2026)
- [KLTNet: Learning Sparse Feature Tracking for Robust and Accurate Monocular Visual-Inertial Odometry](https://mlsanity.com/paper/2608.24544/) (2026)

## Abstract (arXiv)

We present DM-VIO, a monocular visual-inertial odometry system based on two novel techniques called delayed marginalization and pose graph bundle adjustment. DM-VIO performs photometric bundle adjustment with a dynamic weight for visual residuals. We adopt marginalization, which is a popular strategy to keep the update time constrained, but it cannot easily be reversed, and linearization points of connected variables have to be fixed. To overcome this we propose delayed marginalization: The idea is to maintain a second factor graph, where marginalization is delayed. This allows us to later readvance this delayed graph, yielding an updated marginalization prior with new and consistent linearization points. In addition, delayed marginalization enables us to inject IMU information into already marginalized states. This is the foundation of the proposed pose graph bundle adjustment, which we use for IMU initialization. In contrast to prior works on IMU initialization, it is able to capture the full photometric uncertainty, improving the scale estimation. In order to cope with initially unobservable scale, we continue to optimize scale and gravity direction in the main system after IMU initialization is complete. We evaluate our system on the EuRoC, TUM-VI, and 4Seasons datasets, which comprise flying drone, large-scale handheld, and automotive scenarios. Thanks to the proposed IMU initialization, our system exceeds the state of the art in visual-inertial odometry, even outperforming stereo-inertial methods while using only a single camera and IMU. The code will be published at http://vision.in.tum.de/dm-vio