Making of the Image Metrics ‘Emily’ Tech Demo
I have seen some of the other material in the SIGGRAPH Image Metrics presskit posted online [Emily Tech Demo] [‘How To’ video], but not the video that shows the making of the Emily tech demo. So here’s that as well:
At the end, there’s a quote from Peter Plantec about how Image Metrics has finally ‘crossed the uncanny valley’, but seriously, am I the only one who thinks the shading is a bit off, and besides that, what’s the point of laying a duplicate of face directly on top of one in a video? Shouldn’t they have shown her talking in a different setting? Maybe showed how they can remap the animation to a different face? There is no reason not to just use the original plate in this example.
Agree on the shading, but from what I heard they weren’t trying really hard (after all they do animation, not a shading). AFAIK, they did not use all the data Debevec’s group provided and instead used a more traditional shader. Also agreed on “what’s the point?” – a side by side demo, additional viewing angles or even a remapping would be great. I find it remarkable how much difference there still is when they blend to the real face towards the end of the clip.
Comment by Martin — 2008/09/17 @ 5:38 PM
Just to add my voice to the “what’s the point” chorus, I’d say that this technology really doesn’t bring anything new to the plate. Problems with CG actors in movies usually stem from animation and acting. It reminds me of when rotoscope was first used in 2D movies. Everyone thought “It’s so real! That’s it, we just have to trace back Reality! It’s the next step in animation!”. Obviously it wasn’t.
Not to sound too negative though, this shows they have great TDs and modelers (and one cute actress)! 🙂
Comment by Seith — 2008/10/10 @ 8:45 PM