2 Hits in 2.3 sec

APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals [article]

Jiangning Zhang, Liang Liu, Zhucun Xue, Yong Liu
2020 arXiv   pre-print
GeometryPredictor uses extra head pose and blink state signals as well as audio to predict the latent landmark geometry information, while FaceReenactor inputs the face landmark image to reenact the photorealistic  ...  Audio-guided face reenactment aims at generating photorealistic faces using audio information while maintaining the same facial movement as when speaking to a real person.  ...  Such a two-stage design can not only generate photorealistic faces but also fuse pose and blink signals into audio.  ... 
arXiv:2004.14569v1 fatcat:uqogtp4f35avpbqpmo3cqgxxgi

APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment [article]

Jiangning Zhang, Xianfang Zeng, Chao Xu, Jun Chen, Yong Liu, Yunliang Jiang
2020 arXiv   pre-print
Audio-guided face reenactment aims to generate a photorealistic face that has matched facial expression with the input audio.  ...  reference face and drive audio signal as inputs.  ...  Decoupling experiments of pose and eye blink signals. capable of disentangling input signals, i.e. audio, head pose, and eye blink.  ... 
arXiv:2010.13017v1 fatcat:cgglya3urrh7nmbpjqmai37afa