ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer

TL;DR

ReSyncer is a unified framework that rewires style-based generators with a style-injected Transformer to produce high-fidelity, versatile lip-synced facial videos from audio, supporting fast personalization, style transfer, and face swapping.

Contribution

The paper introduces ReSyncer, a novel approach that reconfigures style-based generators with a Transformer for synchronized audio-visual facial generation, enabling multiple applications.

Findings

Produces high-fidelity lip-synced videos from audio.

Supports fast personalized fine-tuning and face swapping.

Enables transfer of speaking styles.

Abstract

Lip-syncing videos with given audio is the foundation for various applications including the creation of virtual presenters or performers. While recent studies explore high-fidelity lip-sync with different techniques, their task-orientated models either require long-term videos for clip-specific training or retain visible artifacts. In this paper, we propose a unified and effective framework ReSyncer, that synchronizes generalized audio-visual facial information. The key design is revisiting and rewiring the Style-based generator to efficiently adopt 3D facial dynamics predicted by a principled style-injected Transformer. By simply re-configuring the information insertion mechanisms within the noise and style space, our framework fuses motion and appearance with unified training. Extensive experiments demonstrate that ReSyncer not only produces high-fidelity lip-synced videos according to audio, but also supports multiple appealing properties that are suitable for creating virtual presenters and performers, including fast personalized fine-tuning, video-driven lip-syncing, the transfer of speaking styles, and even face swapping. Resources can be found at https://guanjz20.github.io/projects/ReSyncer.