VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

TL;DR

VideoReTalking is a comprehensive system that edits real-world talking head videos to match input audio with accurate lip-sync and expression changes, producing high-quality, realistic videos without retraining for individual identities.

Contribution

It introduces a sequential, learning-based pipeline for expression editing, lip-sync, and face enhancement that works universally across different persons without retraining.

Findings

Outperforms state-of-the-art in lip-sync accuracy

Produces higher visual quality in edited videos

Operates effectively on in-the-wild examples

Abstract

We present VideoReTalking, a new system to edit the faces of a real-world talking head video according to input audio, producing a high-quality and lip-syncing output video even with a different emotion. Our system disentangles this objective into three sequential tasks: (1) face video generation with a canonical expression; (2) audio-driven lip-sync; and (3) face enhancement for improving photo-realism. Given a talking-head video, we first modify the expression of each frame according to the same expression template using the expression editing network, resulting in a video with the canonical expression. This video, together with the given audio, is then fed into the lip-sync network to generate a lip-syncing video. Finally, we improve the photo-realism of the synthesized faces through an identity-aware face enhancement network and post-processing. We use learning-based approaches for all three steps and all our modules can be tackled in a sequential pipeline without any user intervention. Furthermore, our system is a generic approach that does not need to be retrained to a specific person. Evaluations on two widely-used datasets and in-the-wild examples demonstrate the superiority of our framework over other state-of-the-art methods in terms of lip-sync accuracy and visual quality.