aiqbench analysis
This paper presents DB-VIO, a novel framework for visual inertial odometry that decouples rotational and translational motion estimation to better handle heterogeneous dynamics in mobile robotics. By integrating depth cues with explicit attitude priors, the method achieves significant performance gains on standard benchmarks like KITTI and EuRoC compared to unified representation baselines. The work advances learning-based VIO by addressing specific limitations in capturing geometric structure within inertial data for autonomous driving and aerial applications.
DB-VIO: Dual-Branch Visual Inertial Odometry with Enhanced Visual-Inertial Representation
arXiv:2607.22123v1 Announce Type: new Abstract: Visual inertial odometry (VIO) is essential for accurate 6-DoF motion estimation in mobile robotic systems. Recent learning-based VIO methods have shown promising progress, but they often rely on unified visual--inertial representations and a single temporal model for full-pose estimation, limiting their ability to capture the heterogeneous dynamics of rotation and translation. Moreover, monocular visual features often lack explicit geometric structure, while raw inertial encoding leaves the underlying rotational kinematics implicit, weakening the rotation-related cues in IMU features. To address these issues, we propose DB-VIO, a dual-branch visual inertial odometry framework with enhanced visual--inertial representation. DB-VIO incorporates depth cues to improve monocular visual perception, injects an explicit integrated-attitude prior to strengthen rotation-aware inertial representation, and decouples pose estimation into dedicated rotational and translational branches for motion-specific temporal modeling. Experiments on autonomous driving and aerial robot benchmarks show that DB-VIO achieves state-of-the-art performance, improving the corresponding baselines by 20\% on KITTI and 33\% on EuRoC. Notably, under the more agile motion patterns of EuRoC, DB-VIO improves the rotational metric by 65.7\% over prior methods. These results demonstrate the effectiveness and generalization of DB-VIO across different platforms and motion scenarios.
Abstract:Visual inertial odometry (VIO) is essential for accurate 6-DoF motion estimation in mobile robotic systems. Recent learning-based VIO methods have shown promising progress, but they often rely on unified visual--inertial representations and a single temporal model for full-pose estimation, limiting their ability to capture the heterogeneous dynamics of rotation and translation. Moreover, monocular visual features often lack explicit geometric structure, while raw inertial encoding leaves the underlying rotational kinematics implicit, weakening the rotation-related cues in IMU features. To address these issues, we propose DB-VIO, a dual-branch visual inertial odometry framework with enhanced visual--inertial representation. DB-VIO incorporates depth cues to improve monocular visual perception, injects an explicit integrated-attitude prior to strengthen rotation-aware inertial representation, and decouples pose estimation into dedicated rotational and translational branches for motion-specific temporal modeling. Experiments on autonomous driving and aerial robot benchmarks show that DB-VIO achieves state-of-the-art performance, improving the corresponding baselines by 20\% on KITTI and 33\% on EuRoC. Notably, under the more agile motion patterns of EuRoC, DB-VIO improves the rotational metric by 65.7\% over prior methods. These results demonstrate the effectiveness and generalization of DB-VIO across different platforms and motion scenarios.
Robotics (cs.RO)
arXiv:2607.22123 [cs.RO]
(or arXiv:2607.22123v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.22123 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 280 words
Related coverage
Dual Quaternion-Based Unscented Kalman Filter with Visual Inertial Odometry for Navigation in GPS-Denied Environments
arXiv · Jun 9, 2026
Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model
arXiv · Jul 23, 2026
FIRE-LIVWO: Robust LiDAR-Inertial-Visual-Wheel Odometry via Failure-Immune mmWave Radar Enhancement
arXiv · Sep 7, 2026
Dual-branch Prompting for Multimodal Machine Translation
arXiv · Jun 17, 2026