Slashdot Mirror


Digital Mouths, Synthetic Faces at MIT and Lucasfilm

jfengel writes "Two separate articles about generating faces automatically. From the Boston Globe, there is a story about MIT scientists putting words into somebody's mouth by splicing together footage. In the samples, I couldn't tell the difference between the synthetic footage and the same person really saying the same thing. (Though it's a little hard to tell at only 81kbps video). And Wired as a lengthy article about generating purely synthetic faces at Lucasfilm. It discusses some of the difficulties in getting it right."

4 of 150 comments (clear)

  1. wow. by morgajel · · Score: 0, Troll

    I feel even more violated about this that I do about face recognition.

    --
    Looking for Book Reviews? Check out Literary Escapism.
  2. scary, scary, scary by ironfroggy · · Score: 1, Troll

    This is some really scary shit. Just think of the possibilities. Like my girlfriend asking for a threeway... hard to resist the temptations possible with this sort of technology isnt it? Maybe it should be banned, limited, etc. But, in order to do that, people would have to know about and care... oh, nevermind. we know we're the only ones that care about these really scary technologies. thats why the internet went bad, only us geeks know the dangers in this sort of thing, and who listens to us?

  3. Hard to tell anything at 82kbps by CmdrTaco+(editor) · · Score: 0, Troll
    I would imagine it would be tough to tell anything at 81kbps. What's the resolution, like 100x100 (I refuse to install Realplayer, so I can't see for myself).

    People seem to be alarmed that this will be used for malicious purposes, but the truth is in order for this to be indistinguishable from real life the "victim" will have to go through a complex semi-3D imaging process using all the possible range of motions of facial muscles. This could hardly be done discretely, at least with todays technology.

    Patching together old footage of someone speaking and changing it into the desired context may work for lower resolutions, but at higher resolutions even sophisticated effects design firms can't do it effectively- think about those cheezy ads for dog food where the puppy dances around.

  4. Re:I've been waiting for this. by Bakajin · · Score: 0, Troll


    Maybe flame bait.. but how wonderfully superficial of you. "I don't care what is in it, so long as it tastes good", "I don't care who pofits, so long as I enjoy it", "I don't care who dies, so long as I get off on it", "I don't care about anything my my own emmediate gratification and don't care to think about anything past that".