Dynamic Gaussian Splatting from Markerless Motion Capture can Reconstruct Infants Movements
This work addresses the need for reliable movement analysis in infants for early detection of neurodevelopmental disabilities, though it appears incremental as it adapts existing techniques to a new domain.
The researchers tackled the problem of 3D movement tracking for clinical populations like infants, where existing algorithms trained on able-bodied adults fail to generalize, by applying dynamic Gaussian splatting to sparse markerless motion capture data with semantic segmentation masks to improve scene initialization. Their results demonstrate the method's potential for rendering novel views and tracking infant movements.
Easy access to precise 3D tracking of movement could benefit many aspects of rehabilitation. A challenge to achieving this goal is that while there are many datasets and pretrained algorithms for able-bodied adults, algorithms trained on these datasets often fail to generalize to clinical populations including people with disabilities, infants, and neonates. Reliable movement analysis of infants and neonates is important as spontaneous movement behavior is an important indicator of neurological function and neurodevelopmental disability, which can help guide early interventions. We explored the application of dynamic Gaussian splatting to sparse markerless motion capture (MMC) data. Our approach leverages semantic segmentation masks to focus on the infant, significantly improving the initialization of the scene. Our results demonstrate the potential of this method in rendering novel views of scenes and tracking infant movements. This work paves the way for advanced movement analysis tools that can be applied to diverse clinical populations, with a particular emphasis on early detection in infants.