Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases

TL;DR

This paper introduces a real-time style modelling system for human locomotion that uses feature-wise transformations and local motion phases, enabling robust and efficient style transfer without reference clips.

Contribution

It presents a novel style modulation network with feature-wise transformations and a contact-free local phase formulation, advancing real-time style transfer in animation.

Findings

More robust style representation

Improved motion quality

Enhanced efficiency in style modelling

Abstract

Controlling the manner in which a character moves in a real-time animation system is a challenging task with useful applications. Existing style transfer systems require access to a reference content motion clip, however, in real-time systems the future motion content is unknown and liable to change with user input. In this work we present a style modelling system that uses an animation synthesis network to model motion content based on local motion phases. An additional style modulation network uses feature-wise transformations to modulate style in real-time. To evaluate our method, we create and release a new style modelling dataset, 100STYLE, containing over 4 million frames of stylised locomotion data in 100 different styles that present a number of challenges for existing systems. To model these styles, we extend the local phase calculation with a contact-free formulation. In comparison to other methods for real-time style modelling, we show our system is more robust and efficient in its style representation while improving motion quality.