End-to-End Motion Capture from Rigid Body Markers with Geodesic Loss
This provides a practical and high-fidelity solution for real-time motion capture in graphics, virtual reality, and biomechanics, though it is incremental as it builds on existing data and methods.
The paper tackles the practical challenges of marker-based motion capture by introducing Rigid Body Markers (RBMs) to simplify setup and using a deep-learning model with geodesic loss to estimate SMPL parameters, achieving state-of-the-art accuracy with over an order of magnitude less computation than optimization-based methods.
Marker-based optical motion capture (MoCap), while long regarded as the gold standard for accuracy, faces practical challenges, such as time-consuming preparation and marker identification ambiguity, due to its reliance on dense marker configurations, which fundamentally limit its scalability. To address this, we introduce a novel fundamental unit for MoCap, the Rigid Body Marker (RBM), which provides unambiguous 6-DoF data and drastically simplifies setup. Leveraging this new data modality, we develop a deep-learning-based regression model that directly estimates SMPL parameters under a geodesic loss. This end-to-end approach matches the performance of optimization-based methods while requiring over an order of magnitude less computation. Trained on synthesized data from the AMASS dataset, our end-to-end model achieves state-of-the-art accuracy in body pose estimation. Real-world data captured using a Vicon optical tracking system further demonstrates the practical viability of our approach. Overall, the results show that combining sparse 6-DoF RBM with a manifold-aware geodesic loss yields a practical and high-fidelity solution for real-time MoCap in graphics, virtual reality, and biomechanics.