MARIO: Motion-Augmented Real-Time Multi-Sensor Inertial Odometry

Yiquan Li, Taeyoung Yeon, Chenfeng Gao, Vasco Xu, Xuanyou Liu, Karan Ahuja; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026, pp. 3460-3469

Inertial odometry (IO) using only Inertial Measurement Units (IMUs) provides a lightweight solution for human motion tracking in augmented reality (AR) and wearable devices. Recent learning-based IO methods have improved the generalizability of inertial localization via large-scale pretraining on human motion datasets. Unfortunately, these approaches remain prone to drift and noise because they fail to capture human motion dynamics, especially on daily activity datasets such as Nymeria. In contrast, we propose to ground inertial odometry in human kinematics through a learned IMU-inferred pose prior that promotes the propagation of physically consistent motion constraints. We integrate our pose prior into existing IO architectures and reduce positional drift by up to 36% in the challenging Nymeria dataset (5x larger than prior works). We further showcase improved long-term performance by developing a sensor-fusion framework that incorporates auxiliary signals from other lightweight sensors such as the magnetometer, barometer, and secondary IMU already available on commercial AR glasses. With our fusion strategy, drift is reduced to 42%, improving robustness and generalization across diverse motion conditions. Together, our results establish a new paradigm for inertial and lightweight odometry, unifying human motion kinematics with multimodal sensing, setting a new benchmark for accurate and robust camera-less human tracking. Our website is available at https://spice-lab.org/projects/MARIO/.