Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

TL;DR

This paper introduces a novel motion-decoupled diffusion framework for generating realistic, audio-driven co-speech gesture videos that maintain appearance details and temporal coherence, surpassing previous skeleton-based methods.

Contribution

It proposes a new nonlinear TPS transformation for motion features and a transformer-based diffusion model for aligned gesture-video generation, enhancing visual quality and temporal consistency.

Findings

Outperforms existing methods in motion quality

Produces more coherent and detailed gesture videos

Effective in preserving appearance information

Abstract

Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural human skeletons, resulting in the omission of appearance information, we focus on the direct generation of audio-driven co-speech gesture videos in this work. There are two main challenges: 1) A suitable motion feature is needed to describe complex human movements with crucial appearance information. 2) Gestures and speech exhibit inherent dependencies and should be temporally aligned even of arbitrary length. To solve these problems, we present a novel motion-decoupled framework to generate co-speech gesture videos. Specifically, we first introduce a well-designed nonlinear TPS transformation to obtain latent motion features preserving essential appearance information. Then a transformer-based diffusion model is proposed to learn the temporal correlation between gestures and speech, and performs generation in the latent motion space, followed by an optimal motion selection module to produce long-term coherent and consistent gesture videos. For better visual perception, we further design a refinement network focusing on missing details of certain areas. Extensive experimental results show that our proposed framework significantly outperforms existing approaches in both motion and video-related evaluations. Our code, demos, and more resources are available at https://github.com/thuhcsi/S2G-MDDiffusion.