Microsoft VASA-1 can fully animate characters from a single photo

[UltraMega]

Quote

The Visual Affective Skills Animator, or VASA, is a machine-learning framework that analyzes a facial photo and then animates it to a voice, syncing the lips and mouth movements to the audio. It also simulates facial expressions, head movements, and even unseen body movements.

Like all generative AI, it isn't perfect. Machines still have trouble with fine details like fingers or, in VASA's case, teeth. Paying close attention to the avatar's teeth, one can see that they change sizes and shape, giving them an accordion-like quality. It is relatively subtle and seems to fluctuate depending on the amount of movement going on in the animation.

 

 

 

https://www.microsoft.com/en-us/research/project/vasa-1/

 

 

 

 

 

 

Edited April 21 by UltraMega

[iamjanco]

While I'll admit that I think the tech behind it is fascinating, examples like the rappin' Mona Lisa above seem to substantiate that we are devolving as a species ( it's got electrolytes comes to mind). 

 

Now show me the progress we've made curing cancer using such tech and you might be able to color me impressed  .

[UltraMega]

18 minutes ago, iamjanco said:

While I'll admit that I think the tech behind it is fascinating, examples like the rappin' Mona Lisa above seem to substantiate that we are devolving as a species ( it's got electrolytes comes to mind). 

 

Now show me the progress we've made curing cancer using such tech and you might be able to color me impressed  .

 

That is definitely the most entertaining bit in the research release, but the rest are much more down to earth. Impressive tech. Remind me of Star Trek or Star Wars sifi stuff when they show pictures of people from the past being animated. That always seemed so far-fetched as a kid, but now it's one of the more simple things for AI to do.