Really interesting to see, it still looks a little cgi'd, so its really cool to see how close we're getting to the uncanny valley. I suppose with some After Effects, you could make it even more difficult see the difference.<p>My only gripe is that there is always so much focus on the face. I understand that its subtleties make for a great research topic; however, I'd love to see this research applied to the full body. Given a full body shot, could we apply the same techniques to gait?<p>One of the major hurdles I see is background estimation if you move a limb (though, this might be able to be resolved with the same techniques used in photoshop for content-aware fill.
"One could also impersonate the facial expressions of someone in more fitting business attire while actually dressed in casual clothing."<p>David Foster Wallace [I misremembered it as before edit Philip K. Dick] predicated this would happen. First it would be used to make you look like you were paying attention then it would be used to make you more presentable. He then predicts that when everyone does this it will have the effect of everyone abandoning video telepresence altogether and just going back to using voice only. I can't find the quote.
I just happened to be playing L.A. Noire recently, which became famous for using motion sensors to transfer actors' facial expressions to their CG version. [1] It looks like this would have them from having to do the whole studio setup and recording for each actor they want to portray.<p>[1] <a href="https://en.wikipedia.org/wiki/Development_of_L.A._Noire#Technical_development" rel="nofollow">https://en.wikipedia.org/wiki/Development_of_L.A._Noire#Tech...</a>
Something was missing from this video, so I fixed it:
<a href="http://www.youtubedoubler.com/?video1=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DeXVspNUeiWw&start1=0&video2=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DMSbzh0w6Ex8&start2=&authorName=" rel="nofollow">http://www.youtubedoubler.com/?video1=https%3A%2F%2Fwww.yout...</a>