github.com/OpenTalker/video-retalking @v0.0.1 sqlite

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

<a target='_blank'>Kun Cheng <sup>*,1,2</sup> </a>&emsp;
<a href='https://vinthony.github.io/' target='_blank'>Xiaodong Cun <sup>*,2</a>&emsp;
<a href='https://yzhang2016.github.io/yongnorriszhang.github.io/' target='_blank'>Yong Zhang <sup>2</sup></a>&emsp;
<a href='https://menghanxia.github.io/' target='_blank'>Menghan Xia <sup>2</sup></a>&emsp;
<a href='https://feiiyin.github.io/' target='_blank'>Fei Yin <sup>2,3</sup></a>&emsp;


<a target='_blank'>Mingrui Zhu <sup>1</sup></a>&emsp;
<a href='https://xuanwangvc.github.io/' target='_blank'>Xuan Wang <sup>2</sup></a>&emsp;
<a href='https://juewang725.github.io/' target='_blank'>Jue Wang <sup>2</sup></a>&emsp;
<a href='https://web.xidian.edu.cn/nnwang/en/index.html' target='_blank'>Nannan Wang <sup>1</sup></a>









<sup>1</sup> Xidian University &emsp; <sup>2</sup> Tencent AI Lab &emsp; <sup>3</sup> Tsinghua University

SIGGRAPH Asia 2022 Conferenence Track

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.

Pipeline

Results in the Wild （contains audio）

https://user-images.githubusercontent.com/4397546/224310754-665eb2dd-aadc-47dc-b1f9-2029a937b20a.mp4

Environment

git clone https://github.com/vinthony/video-retalking.git
cd video-retalking
conda create -n video_retalking python=3.8
conda activate video_retalking
pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html
pip install -r requirements.txt

Quick Inference

Pretrained Models

Please download our pre-trained models and put them in ./checkpoints.

Inference

python3 inference.py \
  --face examples/face/1.mp4 \
  --audio examples/audio/1.wav \
  --outfile results/1_1.mp4

This script includes data preprocessing steps. You can test any talking face videos without manual alignment. But it is worth noting that DNet cannot handle extreme poses.

You can also control the expression by adding the following parameters:

--exp_img: Pre-defined expression template. The default is "neutral". You can choose "smile" or an image path.

--up_face: You can choose "surprise" or "angry" to modify the expression of upper face with GANimation.

Citation

If you find our work useful in your research, please consider citing:

@misc{cheng2022videoretalking,
        title={VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild}, 
        author={Kun Cheng and Xiaodong Cun and Yong Zhang and Menghan Xia and Fei Yin and Mingrui Zhu and Xuan Wang and Jue Wang and Nannan Wang},
        year={2022},
        eprint={2211.14758},
        archivePrefix={arXiv},
        primaryClass={cs.CV}
  }

Acknowledgement

Thanks to Wav2Lip, PIRenderer, GFP-GAN, GPEN, ganimation_replicate, STIT for sharing their code.

Related Work

• StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN (ECCV 2022)
• CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior (CVPR 2023)
• SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation (CVPR 2023)
• DPE: Disentanglement of Pose and Expression for General Video Portrait Editing (CVPR 2023)
• 3D GAN Inversion with Facial Symmetry Prior (CVPR 2023)
• T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations (CVPR 2023)

Disclaimer

This is not an official product of Tencent. This repository can only be used for personal/research/non-commercial purposes.