VASA-1

Microsoft Research Asia (Microsoft Research Asia) recently published a paper introducing the new VASA-1 model, which allows the user to automatically speak to the character in the picture by simply providing a static portrait image and a voice audio clip. What's particularly interesting about VASA-1 is its ability to simulate natural facial expressions, various emotions, and lip synchronization, and most importantly is that it's virtually artifact-free, making it hard to spot if you don't look closely. The researchers admit that, like all other models, the model is currently unable to properly handle non-rigid such as hair...