- formatting
- images
- links
- math
- code
- blockquotes
•
•
•
•
•
READ Avatars: Realistic Emotion-controllable Audio Driven Avatars
A technical summary of READ Avatars — emotion-controllable audio-driven avatar generation using neural rendering and adversarial training. BMVC 2023 Oral.
FACTS: Facial Animation Creation using the Transfer of Styles
A summary of the FACTS paper — retargeting the style of 3D facial animations across emotions and identities while preserving lip sync.
DAE Talking: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder
A summary of DAE-Talking: high-fidelity speech-driven talking face generation using a diffusion autoencoder for expressive digital human animation.
Towards Generating Ultra-High Resolution Talking-Face Videos with Lip-Synchronization
A review of methods for generating ultra high resolution talking face videos with accurate lip synchronization using deep learning.
Should Deepfakes be Open-Sourced?
Should deepfake models be open sourced? A discussion of the ethics, risks, and benefits of open-sourcing AI avatar and lip sync technology.