MotionPersona: Characteristics-aware Locomotion Control

TL;DR

MotionPersona is a real-time character controller that generates diverse, characteristic-aware locomotion by conditioning on traits, prompts, and control signals, outperforming existing methods in quality and diversity.

Contribution

It introduces the first characteristics-aware, real-time locomotion generator conditioned on traits and prompts, with a new dataset and a few-shot characterization technique.

Findings

Outperforms existing methods in motion quality and diversity.

Capable of generating motion reflecting user-specified traits.

Supports real-time response to dynamic control inputs.

Abstract

We present MotionPersona, a novel real-time character controller that allows users to characterize a character by specifying attributes such as physical traits, mental states, and demographics, and projects these properties into the generated motions for animating the character. In contrast to existing deep learning-based controllers, which typically produce homogeneous animations tailored to a single, predefined character, MotionPersona accounts for the impact of various traits on human motion as observed in the real world. To achieve this, we develop a block autoregressive motion diffusion model conditioned on SMPLX parameters, textual prompts, and user-defined locomotion control signals. We also curate a comprehensive dataset featuring a wide range of locomotion types and actor traits to enable the training of this characteristic-aware controller. Unlike prior work, MotionPersona is the first method capable of generating motion that faithfully reflects user-specified characteristics (e.g., an elderly person's shuffling gait) while responding in real time to dynamic control inputs. Additionally, we introduce a few-shot characterization technique as a complementary conditioning mechanism, enabling customization via short motion clips when language prompts fall short. Through extensive experiments, we demonstrate that MotionPersona outperforms existing methods in characteristics-aware locomotion control, achieving superior motion quality and diversity. Results, code, and demo can be found at: https://motionpersona25.github.io/.