Summary
Motion capture systems that track human movements usually need markers placed precisely and cleanly, which is hard to do outside labs. The authors present DirtyMoCap, a system that can take messy, unordered, and noisy marker data and still figure out the body’s pose and shape accurately. They do this by translating the raw marker data into stable 'anchors' corresponding to body joints and surfaces, then fitting a detailed human model to these anchors using a fast and adaptable solver. Their approach works well on many different marker setups and outperforms existing methods, even speeding up computations significantly. They also demonstrate the system by capturing martial arts motions, creating a new dataset of realistic movement recordings.
What this means in practice
- •For motion capture studios: Generate accurate human body poses from irregular and noisy marker data without strict placement rules.
- •For game animation teams: Create detailed character animations from challenging raw motion capture data with fewer setup constraints.
Authors
Long Wang, Shuting Zhao, Shen Yan, Siyuan Yu, Xiaoben Li, Zeyu Cai, Yumeng Hou, Yuliang Xiu
Abstract
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.