# Deep IMU Bias Inference for Robust Visual-Inertial Odometry with Factor Graphs

arXiv: https://arxiv.org/abs/2211.04517 · HTML: https://mlsanity.com/paper/2211.04517/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2022.

## Built on by (most cited first, 13 of 13)

- [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)
- [Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies](https://mlsanity.com/paper/2603.16952/) (2026)
- [EqNIO: Subequivariant Neural Inertial Odometry](https://mlsanity.com/paper/2408.06321/) (2024)
- [AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability](https://mlsanity.com/paper/2501.15659/) (2025)
- [AirIMU: Learning Uncertainty Propagation for Inertial Odometry](https://mlsanity.com/paper/2310.04874/) (2023)
- [Generalizable End-to-End Deep Learning Frameworks for Real-Time Attitude Estimation Using 6DoF Inertial Measurement Units](https://mlsanity.com/paper/2302.06037/) (2023)
- [Learning IMU Bias with Diffusion Model](https://mlsanity.com/paper/2505.11763/) (2025)
- [Multiple and Gyro-Free Inertial Datasets](https://mlsanity.com/paper/2403.15494/) (2024)
- [DynaVINS++: Robust Visual-Inertial State Estimator in Dynamic Environments by Adaptive Truncated Least Squares and Stable State Recovery](https://mlsanity.com/paper/2410.15373/) (2024)
- [A Plug-and-Play Learning-based IMU Bias Factor for Robust Visual-Inertial Odometry](https://mlsanity.com/paper/2503.12527/) (2025)
- [X-IONet: Cross-Platform Inertial Odometry Network for Pedestrian and Legged Robot](https://mlsanity.com/paper/2511.08277/) (2025)
- [GINIO: A Geometric SO(3)-Equivariant Interface for Neural Inertial Odometry](https://mlsanity.com/paper/2609.25338/) (2026)

## Abstract (arXiv)

Visual Inertial Odometry (VIO) is one of the most established state estimation methods for mobile platforms. However, when visual tracking fails, VIO algorithms quickly diverge due to rapid error accumulation during inertial data integration. This error is typically modeled as a combination of additive Gaussian noise and a slowly changing bias which evolves as a random walk. In this work, we propose to train a neural network to learn the true bias evolution. We implement and compare two common sequential deep learning architectures: LSTMs and Transformers. Our approach follows from recent learning-based inertial estimators, but, instead of learning a motion model, we target IMU bias explicitly, which allows us to generalize to locomotion patterns unseen in training. We show that our proposed method improves state estimation in visually challenging situations across a wide range of motions by quadrupedal robots, walking humans, and drones. Our experiments show an average 15% reduction in drift rate, with much larger reductions when there is total vision failure. Importantly, we also demonstrate that models trained with one locomotion pattern (human walking) can be applied to another (quadruped robot trotting) without retraining.