OpenMoCap: Rethinking Optical Motion Capture under Real-world Occlusion

TL;DR

OpenMoCap introduces a new model and dataset to improve optical motion capture accuracy under real-world occlusion conditions, addressing limitations of existing methods.

Contribution

The paper presents the CMU-Occlu dataset with realistic occlusion simulation and the OpenMoCap model that captures long-range marker dependencies for robust motion capture.

Findings

OpenMoCap outperforms existing methods in diverse scenarios.

The CMU-Occlu dataset enables better training for occlusion scenarios.

OpenMoCap is integrated into a practical motion capture system.

Abstract

Optical motion capture is a foundational technology driving advancements in cutting-edge fields such as virtual reality and film production. However, system performance suffers severely under large-scale marker occlusions common in real-world applications. An in-depth analysis identifies two primary limitations of current models: (i) the lack of training datasets accurately reflecting realistic marker occlusion patterns, and (ii) the absence of training strategies designed to capture long-range dependencies among markers. To tackle these challenges, we introduce the CMU-Occlu dataset, which incorporates ray tracing techniques to realistically simulate practical marker occlusion patterns. Furthermore, we propose OpenMoCap, a novel motion-solving model designed specifically for robust motion capture in environments with significant occlusions. Leveraging a marker-joint chain inference mechanism, OpenMoCap enables simultaneous optimization and construction of deep constraints between markers and joints. Extensive comparative experiments demonstrate that OpenMoCap consistently outperforms competing methods across diverse scenarios, while the CMU-Occlu dataset opens the door for future studies in robust motion solving. The proposed OpenMoCap is integrated into the MoSen MoCap system for practical deployment. The code is released at: https://github.com/qianchen214/OpenMoCap.