Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kraiger, Keaton, Li, Jingjing, Bharadwaj, Skanda, Scott, Jesse, Collins, Robert T., Liu, Yanxi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.19170
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917130442637312
author Kraiger, Keaton
Li, Jingjing
Bharadwaj, Skanda
Scott, Jesse
Collins, Robert T.
Liu, Yanxi
author_facet Kraiger, Keaton
Li, Jingjing
Bharadwaj, Skanda
Scott, Jesse
Collins, Robert T.
Liu, Yanxi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19170
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FootFormer: Estimating Stability from Visual Input
Kraiger, Keaton
Li, Jingjing
Bharadwaj, Skanda
Scott, Jesse
Collins, Robert T.
Liu, Yanxi
Computer Vision and Pattern Recognition
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.
title FootFormer: Estimating Stability from Visual Input
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.19170