mikejuk writes: If you always wanted to see John Wayne play the lead in The Good, the Bad and the Ugly, you might not have to wait much longer. A University of Washington team has essentially reversed engineered what makes an actor recognizable as that actor, or as the title of the paper puts it, "What Makes Tom Hanks Look Like Tom Hanks." It explains how using nothing but photos and videos from the web it is possible to create an actor puppet that follows the expressions of a driver (i.e. a puppeteer). Now you really can see actors perform things they never got around to performing. The model of the "puppet" is first created using photos from the web. The next stage is to analyze a video of the "driver", i.e. to work out the deformations in the puppet needed to make it follow the driver. ... What they discovered: "After a great deal of experimentation, we obtained surprisingly convincing results using the following simple recipe: use actor B's shape, B's texture, and A's motion (adjusted for the geometry of B's face)."
Nothing in progression can rest on its original plan. We may as well think of
rocking a grown man in the cradle of an infant. -- Edmund Burke