Conditional Motion In-betweening
This work addresses the need for more controllable motion generation in practical applications like animation or robotics, though it appears incremental by building on existing in-betweening methods.
The paper tackles the problem of generating intermediate skeletal motion between start and target poses, focusing on improving controllability to satisfy semantic contexts, and reports outperforming state-of-the-art methods in pose prediction errors.
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.