FootFormer: Estimating Stability from Visual Input
This work addresses the need for accurate stability estimation in kinesiology and related fields, representing an incremental improvement over existing methods.
The paper tackles the problem of predicting human motion dynamics from visual input, achieving state-of-the-art performance in estimating stability-predictive components like center of pressure and center of mass on multiple datasets.
We propose FootFormer, a cross-modality approach for jointly predicting human motion dynamics directly from visual input. On multiple datasets, FootFormer achieves statistically significantly better or equivalent estimates of foot pressure distributions, foot contact maps, and center of mass (CoM), as compared with existing methods that generate one or two of those measures. Furthermore, FootFormer achieves SOTA performance in estimating stability-predictive components (CoP, CoM, BoS) used in classic kinesiology metrics. Code and data are available at https://github.com/keatonkraiger/Vision-to-Stability.git.