… In this work, we propose a novel face reenactment network, Audio-Visual Face Reenactment
GAN. Our network uses audio-visual cues to reenact a source image according to a driving …

… To enable photo-realistic facial reenactment based on audio signals, we employ a 3D face
… a high audio-visual sync, similar to state-of-the-art video-based reenactment approaches …

… shot talking face generation with a high-resolution audio-visual … face generation by
adversarially disentangled audio-visual … talking face generation by implicitly modularized …

… 3D face reenactment, which involves manipulating face images … realistic faces, existing
face reenactment technology still faces … Besides, face reenactment involves a large amount of …

… -subject reenactment. In this work, we propose an effective and cost-efficient face reenactment
… In Table 1 we summarize the key features of representative face reenactment methods …

… Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, …

… , existing face reenactment methods rely on a set of target faces for learning subject-specific
traits. However, in real-world scenario end-users often only have one target face at hand, …

… face generation by learning disentangled audio-visual representation. We find that the talking
face … We also demonstrate the learned audio-visual representation is extremely useful for …

… To seamlessly connect different clips in the reenactment, we … to find the optimal order of the
reenacted frames. Our system … A large-scale audio-visual dataset for emotional talking-face …

… reenacted face. Finally, we generate a photorealistic video portrait from the reenacted synthetic
face sequence via a neural face … to learn a disentangled audio-visual representation in a …