AStF: Motion Style Transfer via Adaptive Statistics Fusor

TL;DR

This paper introduces AStF, a novel method for human motion style transfer that incorporates higher-order statistical coefficients, such as skewness and kurtosis, to better capture complex motion dynamics and improve transfer quality.

Contribution

The paper proposes a new Adaptive Statistics Fusor (AStF) that integrates high-order statistics for more effective motion style transfer, surpassing existing methods.

Findings

AStF outperforms state-of-the-art methods in motion style transfer quality.

Inclusion of skewness and kurtosis improves the modeling of motion dynamics.

Experimental results demonstrate the effectiveness of the proposed approach.

Abstract

Human motion style transfer allows characters to appear less rigidity and more realism with specific style. Traditional arbitrary image style transfer typically process mean and variance which is proved effective. Meanwhile, similar methods have been adapted for motion style transfer. However, due to the fundamental differences between images and motion, relying on mean and variance is insufficient to fully capture the complex dynamic patterns and spatiotemporal coherence properties of motion data. Building upon this, our key insight is to bring two more coefficient, skewness and kurtosis, into the analysis of motion style. Specifically, we propose a novel Adaptive Statistics Fusor (AStF) which consists of Style Disentanglement Module (SDM) and High-Order Multi-Statistics Attention (HOS-Attn). We trained our AStF in conjunction with a Motion Consistency Regularization (MCR) discriminator. Experimental results show that, by providing a more comprehensive model of the spatiotemporal statistical patterns inherent in dynamic styles, our proposed AStF shows proficiency superiority in motion style transfers over state-of-the-arts. Our code and model are available at https://github.com/CHMimilanlan/AStF.