Audio-Visual Face Reenactment

TL;DR

This paper introduces a new audio-visual face reenactment method that generates realistic talking head videos by transferring head motion and improving lip sync quality, achieving state-of-the-art results.

Contribution

The proposed approach combines dense motion transfer, audio cues, face priors, and an identity-aware generator to enhance realism and generalization in face reenactment.

Findings

Outperforms existing methods quantitatively and qualitatively.

Generalizes well to unseen faces, languages, and voices.

Produces high-quality, detailed talking head videos.

Abstract

This work proposes a novel method to generate realistic talking head videos using audio and visual streams. We animate a source image by transferring head motion from a driving video using a dense motion field generated using learnable keypoints. We improve the quality of lip sync using audio as an additional input, helping the network to attend to the mouth region. We use additional priors using face segmentation and face mesh to improve the structure of the reconstructed faces. Finally, we improve the visual quality of the generations by incorporating a carefully designed identity-aware generator module. The identity-aware generator takes the source image and the warped motion features as input to generate a high-quality output with fine-grained details. Our method produces state-of-the-art results and generalizes well to unseen faces, languages, and voices. We comprehensively evaluate our approach using multiple metrics and outperforming the current techniques both qualitative and quantitatively. Our work opens up several applications, including enabling low bandwidth video calls. We release a demo video and additional information at http://cvit.iiit.ac.in/research/projects/cvit-projects/avfr.