Taming Diffusion Probabilistic Models for Character Control

TL;DR

This paper introduces a transformer-based diffusion model for real-time, diverse, and high-quality character animation control driven by user inputs, advancing the capabilities of interactive character animation systems.

Contribution

The paper presents the first real-time character control framework using a diffusion probabilistic model with novel algorithmic designs for enhanced diversity and controllability.

Findings

Supports multiple animation styles with a single model

Outperforms existing character controllers in diversity and quality

Enables real-time, user-driven character animation

Abstract

We present a novel character control framework that effectively utilizes motion diffusion probabilistic models to generate high-quality and diverse character animations, responding in real-time to a variety of dynamic user-supplied control signals. At the heart of our method lies a transformer-based Conditional Autoregressive Motion Diffusion Model (CAMDM), which takes as input the character's historical motion and can generate a range of diverse potential future motions conditioned on high-level, coarse user control. To meet the demands for diversity, controllability, and computational efficiency required by a real-time controller, we incorporate several key algorithmic designs. These include separate condition tokenization, classifier-free guidance on past motion, and heuristic future trajectory extension, all designed to address the challenges associated with taming motion diffusion probabilistic models for character control. As a result, our work represents the first model that enables real-time generation of high-quality, diverse character animations based on user interactive control, supporting animating the character in multiple styles with a single unified model. We evaluate our method on a diverse set of locomotion skills, demonstrating the merits of our method over existing character controllers. Project page and source codes: https://aiganimation.github.io/CAMDM/