Homogeneous Dynamics Space for Heterogeneous Humans

TL;DR

This paper introduces Homogeneous Dynamics Space (HDyS), a unified framework that aggregates diverse human motion data to better understand human dynamics through a homogeneous latent space.

Contribution

It proposes HDyS, a novel approach to unify heterogeneous human motion data into a single homogeneous space, advancing data-driven human dynamics understanding.

Findings

HDyS effectively maps human kinematics to dynamics.

The approach demonstrates robust performance across multiple datasets.

HDyS provides a foundational space for future human motion analysis.

Abstract

Analyses of human motion kinematics have achieved tremendous advances. However, the production mechanism, known as human dynamics, is still undercovered. In this paper, we aim to push data-driven human dynamics understanding forward. We identify a major obstacle to this as the heterogeneity of existing human motion understanding efforts. Specifically, heterogeneity exists in not only the diverse kinematics representations and hierarchical dynamics representations but also in the data from different domains, namely biomechanics and reinforcement learning. With an in-depth analysis of the existing heterogeneity, we propose to emphasize the beneath homogeneity: all of them represent the homogeneous fact of human motion, though from different perspectives. Given this, we propose Homogeneous Dynamics Space (HDyS) as a fundamental space for human dynamics by aggregating heterogeneous data and training a homogeneous latent space with inspiration from the inverse-forward dynamics procedure. Leveraging the heterogeneous representations and datasets, HDyS achieves decent mapping between human kinematics and dynamics. We demonstrate the feasibility of HDyS with extensive experiments and applications. The project page is https://foruck.github.io/HDyS.