Conditional Motion In-betweening

TL;DR

This paper introduces a unified method for pose and semantic conditioned motion in-betweening that improves motion quality and controllability, outperforming existing techniques in pose prediction accuracy.

Contribution

A novel unified model for pose and semantic conditioned motion in-betweening, with a motion augmentation technique to enhance motion quality.

Findings

Outperforms state-of-the-art in pose prediction errors

Provides enhanced controllability in motion generation

Uses motion augmentation to define smooth trajectory distributions

Abstract

Motion in-betweening (MIB) is a process of generating intermediate skeletal movement between the given start and target poses while preserving the naturalness of the motion, such as periodic footstep motion while walking. Although state-of-the-art MIB methods are capable of producing plausible motions given sparse key-poses, they often lack the controllability to generate motions satisfying the semantic contexts required in practical applications. We focus on the method that can handle pose or semantic conditioned MIB tasks using a unified model. We also present a motion augmentation method to improve the quality of pose-conditioned motion generation via defining a distribution over smooth trajectories. Our proposed method outperforms the existing state-of-the-art MIB method in pose prediction errors while providing additional controllability.