SyncAnimation: A Real-Time End-to-End Framework for Audio-Driven Human Pose and Talking Head Animation

TL;DR

SyncAnimation is a novel real-time framework that uses NeRF to generate high-quality, audio-synchronized talking avatars with detailed facial expressions and upper body movements, addressing previous computational and realism limitations.

Contribution

It introduces the first NeRF-based method combining audio-to-pose and audio-to-expression synchronization for real-time, high-fidelity talking avatar generation.

Findings

Achieves high-precision pose and expression generation.

Ensures seamless audio-synchronized lip and upper body movements.

Operates in real-time with high visual quality.

Abstract

Generating talking avatar driven by audio remains a significant challenge. Existing methods typically require high computational costs and often lack sufficient facial detail and realism, making them unsuitable for applications that demand high real-time performance and visual quality. Additionally, while some methods can synchronize lip movement, they still face issues with consistency between facial expressions and upper body movement, particularly during silent periods. In this paper, we introduce SyncAnimation, the first NeRF-based method that achieves audio-driven, stable, and real-time generation of speaking avatar by combining generalized audio-to-pose matching and audio-to-expression synchronization. By integrating AudioPose Syncer and AudioEmotion Syncer, SyncAnimation achieves high-precision poses and expression generation, progressively producing audio-synchronized upper body, head, and lip shapes. Furthermore, the High-Synchronization Human Renderer ensures seamless integration of the head and upper body, and achieves audio-sync lip. The project page can be found at https://syncanimation.github.io