Transformer IMU Calibrator: Dynamic On-body IMU Calibration for Inertial Motion Capture

2025-06-12

AI Summary

Conventional calibration methods for sparse inertial motion capture rely on the restrictive static-assumption hypothesis—that both the coordinate-system drift (R_G'G) and sensor bias (R_BS) remain constant—requiring dedicated stationary calibration phases. This assumption severely limits practicality and long-term accuracy. Method: We propose the first online dynamic calibration framework that eliminates the need for static initialization. Our approach employs a Transformer-based end-to-end mapping model trained on synthetic paired data and incorporates an IMU-readings-diversity-driven adaptive triggering mechanism. Theoretically, we replace the static assumption with a relaxed “short-term slow-variation + motion diversity” dual hypothesis, enabling implicit, calibration-free dynamic estimation. Contribution/Results: The method achieves real-time estimation of R_G'G and R_BS within multi-second motion windows, significantly improving long-duration capture accuracy. Source code and dataset are publicly released.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this paper, we propose a novel dynamic calibration method for sparse inertial motion capture systems, which is the first to break the restrictive absolute static assumption in IMU calibration, i.e., the coordinate drift RG'G and measurement offset RBS remain constant during the entire motion, thereby significantly expanding their application scenarios. Specifically, we achieve real-time estimation of RG'G and RBS under two relaxed assumptions: i) the matrices change negligibly in a short time window; ii) the human movements/IMU readings are diverse in such a time window. Intuitively, the first assumption reduces the number of candidate matrices, and the second assumption provides diverse constraints, which greatly reduces the solution space and allows for accurate estimation of RG'G and RBS from a short history of IMU readings in real time. To achieve this, we created synthetic datasets of paired RG'G, RBS matrices and IMU readings, and learned their mappings using a Transformer-based model. We also designed a calibration trigger based on the diversity of IMU readings to ensure that assumption ii) is met before applying our method. To our knowledge, we are the first to achieve implicit IMU calibration (i.e., seamlessly putting IMUs into use without the need for an explicit calibration process), as well as the first to enable long-term and accurate motion capture using sparse IMUs. The code and dataset are available at https://github.com/ZuoCX1996/TIC.

Problem

• Dynamic calibration for sparse inertial motion capture systems
• Real-time estimation of coordinate drift and measurement offset
• Implicit IMU calibration without explicit calibration process

Innovation

• Transformer-based model for IMU calibration
• Real-time estimation with relaxed assumptions
• Implicit calibration without explicit process