解决真实场景下标记物遮挡导致的动作捕捉难题
OpenMoCap: Rethinking Optical Motion Capture under Real-world Occlusion
- 设计标记-关节链推理机制，同时优化标记与关节关系
- 在复杂遮挡下动作重建误差比现有方法低17.3%
- 适合虚拟现实、影视制作等真实场景中的高鲁棒性捕捉
光学动作捕捉是虚拟现实和影视制作等前沿领域的重要技术，但在真实应用中普遍存在的大规模标记物遮挡会严重降低系统性能。深入分析发现当前模型存在两大缺陷：(i) 缺乏能真实反映标记物遮挡模式的训练数据；(ii) 缺少捕捉标记物间长程依赖的训练策略。为此，我们构建了CMU-Occlu数据集，利用光线追踪技术真实模拟实际遮挡情况。同时提出OpenMoCap模型，专为高遮挡环境设计，通过标记-关节链推理机制，实现标记与关节间的深度约束联合优化。大量对比实验表明，OpenMoCap在多种场景下均显著优于现有方法，且所提出的数据集为未来鲁棒动作求解研究提供支持。该模型已集成至MoSen MoCap系统用于实际部署，代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。