• Corpus ID: 233169178

Everything's Talkin': Pareidolia Face Reenactment

@article{Song2021EverythingsTP,
  title={Everything's Talkin': Pareidolia Face Reenactment},
  author={Linsen Song and Wayne Wu and Chaoyou Fu and Chen Qian and Chen Change Loy and Ran He},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.03061}
}

• Linsen Song, Wayne Wu, +3 authors R. He
• Published 7 April 2021
• Computer Science
• ArXiv

We present a new application direction named Pareidolia Face Reenactment, which is defined as animating a static illusory face to move in tandem with a human face in the video. For the large differences between pareidolia face reenactment and traditional human face reenactment, two main challenges are introduced, i.e., shape variance and texture variance. In this work, we propose a novel Parametric Unsupervised Reenactment Algorithm to tackle these two challenges. Specifically, we propose to decompose the reenactment into three catenate processes: shape modeling, motion transfer and texture synthesis. With the decomposition, we introduce three crucial components, i.e., Parametric Shape Modeling, Expansionary Motion Transfer and Unsupervised Texture Synthesizer, to overcome the problems brought by the remarkably variances on pareidolia faces. Extensive experiments show the superior performance of our method both qualitatively and quantitatively. Code, model and data are available on our project page1. *Equal contribution. †Corresponding author. 1https://wywu.github.io/projects/ETT/ETT.html