# DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints

arXiv: https://arxiv.org/abs/1906.11435 · HTML: https://mlsanity.com/paper/1906.11435/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2019.

## Built on by (most cited first, 27 of 27)

- [SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images](https://mlsanity.com/paper/2302.04233/) (2023)
- [Deep Learning for Inertial Positioning: A Survey](https://mlsanity.com/paper/2303.03757/) (2023)
- [Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics](https://mlsanity.com/paper/2207.04680/) (2022)
- [Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection](https://mlsanity.com/paper/2205.06187/) (2022)
- [Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy](https://mlsanity.com/paper/2406.16087/) (2024)
- [iSLAM: Imperative SLAM](https://mlsanity.com/paper/2306.07894/) (2023)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [DVI-SLAM: A Dual Visual Inertial SLAM Network](https://mlsanity.com/paper/2309.13814/) (2023)
- [Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth](https://mlsanity.com/paper/2203.01557/) (2022)
- [Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation: A Comprehensive Review](https://mlsanity.com/paper/2302.11089/) (2023)
- [MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM](https://mlsanity.com/paper/2509.20757/) (2025)
- [Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments](https://mlsanity.com/paper/2304.07250/) (2023)
- [Learned Monocular Depth Priors in Visual-Inertial Initialization](https://mlsanity.com/paper/2204.09171/) (2022)
- [CUAHN-VIO: Content-and-Uncertainty-Aware Homography Network for Visual-Inertial Odometry](https://mlsanity.com/paper/2208.13935/) (2022)
- [Generalizable End-to-End Deep Learning Frameworks for Real-Time Attitude Estimation Using 6DoF Inertial Measurement Units](https://mlsanity.com/paper/2302.06037/) (2023)
- [Causal Transformer for Fusion and Pose Estimation in Deep Visual Inertial Odometry](https://mlsanity.com/paper/2409.08769/) (2024)
- [Learning Interpretable BEV Based VIO without Deep Neural Networks](https://mlsanity.com/paper/2109.12292/) (2021)
- [Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression](https://mlsanity.com/paper/2208.00919/) (2022)
- [GenDepth: Generalizing Monocular Depth Estimation for Arbitrary Camera Parameters via Ground Plane Embedding](https://mlsanity.com/paper/2312.06021/) (2023)
- [OdoNet: Untethered Speed Aiding for Vehicle Navigation Without Hardware Wheeled Odometer](https://mlsanity.com/paper/2109.03091/) (2021)
- [TTCDist: Fast Distance Estimation From an Active Monocular Camera Using Time-to-Contact](https://mlsanity.com/paper/2203.07530/) (2022)
- [NOCaL: Calibration-Free Semi-Supervised Learning of Odometry and Camera Intrinsics](https://mlsanity.com/paper/2210.07435/) (2022)
- [A Real-Time Fusion Framework for Long-term Visual Localization](https://mlsanity.com/paper/2210.09757/) (2022)
- [Dual-Agent Reinforcement Learning for Adaptive and Cost-Aware Visual-Inertial Odometry](https://mlsanity.com/paper/2511.21083/) (2025)
- [Mono-Hydra++: Real-Time Monocular Scene Graph Construction with Multi-Task Learning for 3D Indoor Mapping](https://mlsanity.com/paper/2605.17661/) (2026)
- [ADM-Fusion: Adaptive Deep Multi-Sensor Fusion for Robust Ego-Motion Estimation in Diverse Conditions](https://mlsanity.com/paper/2606.25111/) (2026)
- [DAP-Pose: Deep Temporal Alignment and Physics-aware Cross-modal Sensor Fusion for Robust Pose Estimation](https://mlsanity.com/paper/2607.23755/) (2026)

## Abstract (arXiv)

This paper presents an self-supervised deep learning network for monocular visual inertial odometry (named DeepVIO). DeepVIO provides absolute trajectory estimation by directly merging 2D optical flow feature (OFF) and Inertial Measurement Unit (IMU) data. Specifically, it firstly estimates the depth and dense 3D point cloud of each scene by using stereo sequences, and then obtains 3D geometric constraints including 3D optical flow and 6-DoF pose as supervisory signals. Note that such 3D optical flow shows robustness and accuracy to dynamic objects and textureless environments. In DeepVIO training, 2D optical flow network is constrained by the projection of its corresponding 3D optical flow, and LSTM-style IMU preintegration network and the fusion network are learned by minimizing the loss functions from ego-motion constraints. Furthermore, we employ an IMU status update scheme to improve IMU pose estimation through updating the additional gyroscope and accelerometer bias. The experimental results on KITTI and EuRoC datasets show that DeepVIO outperforms state-of-the-art learning based methods in terms of accuracy and data adaptability. Compared to the traditional methods, DeepVIO reduces the impacts of inaccurate Camera-IMU calibrations, unsynchronized and missing data.