GRAICVLGJan 12, 2022

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

arXiv:2201.04439v198 citations
AI Analysis

This work addresses the problem of real-time style control in animation systems for applications like gaming or virtual reality, representing an incremental advancement over prior style transfer methods.

The paper tackles the challenge of real-time style modeling for character animation by introducing a system that uses feature-wise transformations and local motion phases, demonstrating improved robustness and motion quality over existing methods on a new dataset with 100 styles.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes