Real-time Controllable Motion Transition for Characters

TL;DR

This paper introduces a real-time motion transition method for characters that ensures high quality, controllability, and speed, suitable for game development and animation pipelines, by learning a motion manifold and conditioned sampling.

Contribution

It proposes a novel real-time transition approach using a motion manifold and conditional sampling, enabling high-quality, controllable, and fast motion transitions without offline computation.

Findings

Generates high-quality motions under multiple metrics.

Robust to various target frames, including extreme cases.

Validated on different datasets with no post-processing needed.

Abstract

Real-time in-between motion generation is universally required in games and highly desirable in existing animation pipelines. Its core challenge lies in the need to satisfy three critical conditions simultaneously: quality, controllability and speed, which renders any methods that need offline computation (or post-processing) or cannot incorporate (often unpredictable) user control undesirable. To this end, we propose a new real-time transition method to address the aforementioned challenges. Our approach consists of two key components: motion manifold and conditional transitioning. The former learns the important low-level motion features and their dynamics; while the latter synthesizes transitions conditioned on a target frame and the desired transition duration. We first learn a motion manifold that explicitly models the intrinsic transition stochasticity in human motions via a multi-modal mapping mechanism. Then, during generation, we design a transition model which is essentially a sampling strategy to sample from the learned manifold, based on the target frame and the aimed transition duration. We validate our method on different datasets in tasks where no post-processing or offline computation is allowed. Through exhaustive evaluation and comparison, we show that our method is able to generate high-quality motions measured under multiple metrics. Our method is also robust under various target frames (with extreme cases).