READ Avatars: Realistic Emotion-controllable Audio Driven Avatars
Author(s): Jack Saunders Originally published on Towards AI. Adding Emotional Control to Audio-Driven Deepfakes READ Avatars takes a reference video and any audio and can produce lip-synced videos in any emotion with fine-grained control over the intensity. One of the critical limitations …
What We Called “Deepfakes” Are No Longer Fakes: How To Use the Technology for Good
Author(s): Ivan Altsybieiev Originally published on Towards AI. Artificial Intelligence, Technology How people use synthetic media to facilitate personalized communication We have been working on machine learning for nine years. Today our face swap app Reface is used by millions of people …
DAE Talking: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder
Author(s): Jack Saunders Originally published on Towards AI. Diffusion Models + Lots of Data = Practically Perfect Talking Head Generation Today we will discuss a new paper and possibly the highest-quality audio-driven deepfake model I have come across. Coming from Microsoft Research, …
Vector Quantization & VQ-GAN
Author(s): Jack Saunders Originally published on Towards AI. Towards Generating Ultra-High Resolution Talking-Face Videos with Lip-Synchronization Results of this paper on a section of silence. on a section Image Credits: Gupta et. al. Towards Generating Ultra-High Resolution Talking-Face Videos with Lip Synchronization …
Popular posts
Updates
Recent Posts
