发表机构
Zhejiang University; Westlake University; Fudan University; National University of Defense Technology; Nanjing University; National University of Singapore（浙江大学; 西湖大学; 复旦大学; 国防科技大学; 南京大学; 新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对光学运动捕捉中无约束标记的鲁棒性问题，提出DirtyMoCap框架，通过代理锚点映射和可微高斯-牛顿求解器，实现任意布局下的高精度重建，并加速百倍。
AI 中文摘要
光学运动捕捉能够提供高保真的人体运动，但其对严格标记布局和干净轨迹的依赖严重限制了其在现实世界中的适用性。在实践中，跟踪系统经常输出无约束标记：稀疏、嘈杂且无序的点云，其配置未知或变化。为了弥合损坏的原始标记与参数化人体模型之间的差距，我们引入了DirtyMoCap，一个鲁棒的、无需标记布局的框架。我们的核心见解是将无序的标记观测映射到一组固定的“代理锚点”，这些锚点由骨骼关节和身体表面点组成，作为稳定的中间表示。我们首先使用循环滑动窗口架构在长序列上初始化并跟踪这些锚点。然后，一个自定义的可微高斯-牛顿求解器将SMPL-H模型拟合到跟踪的锚点上，以恢复全身姿态、平移和形状。通过显式推导几何残差，我们的求解器以端到端的方式学习自适应观测置信度、平滑度和先验权重，动态适应输入数据的可靠性。在多样、嘈杂的标记配置上进行的大量实验表明，DirtyMoCap仅使用单个训练模型即可成功泛化到任意布局。它在关节和顶点重建精度方面始终优于最先进的特定配置基线，同时我们自定义的CUDA求解器相比标准PyTorch实现实现了高达100倍的加速。我们进一步将DirtyMoCap应用于中国传统武术的异构原始光学MoCap记录，生成了一个时间上连贯的SMPL-H重建的功夫运动数据集。代码和数据可在该https URL获取。
英文摘要
Optical motion capture delivers high-fidelity human motion, but its reliance on strict marker layouts and clean trajectories severely limits its real-world applicability. In practice, tracking systems frequently output unconstrained markers: sparse, noisy, and unordered point clouds with unknown or varying configurations. To bridge the gap between corrupted raw markers and parametric human models, we introduce DirtyMoCap, a robust, marker-layout-free framework. Our core insight is to map unordered marker observations to a fixed set of "proxy anchors" comprising skeletal joints and body surface points, which serve as a stable intermediate representation. We first initialize and track these anchors over long sequences using a recurrent sliding-window architecture. Then, a custom differentiable Gauss-Newton solver fits the SMPL-H model to the tracked anchors to recover full-body pose, translation, and shape. By explicitly deriving geometric residuals, our solver learns adaptive observation confidence, smoothness, and prior weights end-to-end, adapting dynamically to the reliability of the input data. Extensive experiments on diverse, noisy marker configurations demonstrate that DirtyMoCap successfully generalizes across arbitrary layouts using only a single trained model. It consistently outperforms state-of-the-art configuration-specific baselines in both joint and vertex reconstruction accuracy, while our custom CUDA solver achieves up to a 100x speedup over standard PyTorch implementations. We further apply DirtyMoCap to heterogeneous raw optical MoCap recordings of traditional Chinese martial arts, yielding a Kung Fu motion dataset of temporally coherent SMPL-H reconstructions. Code and data are available at https://wanglongzju.github.io/DirtyMoCap-Project-Page.
CommentsHomepage: https://wanglongzju.github.io/DirtyMoCap-Project-Page
