Orientation-Aware Leg Movement Learning for Action-Driven Human Motion Prediction

TL;DR

This paper introduces an orientation-aware in-betweening approach for human motion prediction that improves transition naturalness by incorporating realistic leg movements, without requiring labeled transition data.

Contribution

It proposes a novel action-conditioned in-betweening learning method that enhances transition realism in human motion prediction, especially for gait-related actions, without using transition labels during training.

Findings

Achieves state-of-the-art results on three benchmark datasets.

Produces more natural and realistic motion transitions.

Generalizes well across unseen large-scale datasets.

Abstract

The task of action-driven human motion prediction aims to forecast future human motion based on the observed sequence while respecting the given action label. It requires modeling not only the stochasticity within human motion but the smooth yet realistic transition between multiple action labels. However, the fact that most datasets do not contain such transition data complicates this task. Existing work tackles this issue by learning a smoothness prior to simply promote smooth transitions, yet doing so can result in unnatural transitions especially when the history and predicted motions differ significantly in orientations. In this paper, we argue that valid human motion transitions should incorporate realistic leg movements to handle orientation changes, and cast it as an action-conditioned in-betweening (ACB) learning task to encourage transition naturalness. Because modeling all possible transitions is virtually unreasonable, our ACB is only performed on very few selected action classes with active gait motions, such as Walk or Run. Specifically, we follow a two-stage forecasting strategy by first employing the motion diffusion model to generate the target motion with a specified future action, and then producing the in-betweening to smoothly connect the observation and prediction to eventually address motion prediction. Our method is completely free from the labeled motion transition data during training. To show the robustness of our approach, we generalize our trained in-betweening learning model on one dataset to two unseen large-scale motion datasets to produce natural transitions. Extensive experimental evaluations on three benchmark datasets demonstrate that our method yields the state-of-the-art performance in terms of visual quality, prediction accuracy, and action faithfulness.