Wed, Nov 20, 12:42 AM CST

Renderosity Forums / Poser - OFFICIAL



Welcome to the Poser - OFFICIAL Forum

Forum Coordinators: RedPhantom

Poser - OFFICIAL F.A.Q (Last Updated: 2024 Nov 18 10:25 pm)



Subject: Pretty amazing CG facial animation technology...


jeffg3 ( ) posted Mon, 18 August 2008 at 9:31 PM · edited Thu, 31 October 2024 at 4:15 PM

http://www.awntv.com/videos/image-metrics-emily-project

"Image Metrics set out to create the world's first completely convincing photo-real CG face at HD resolution. For the effect to be believable, CG Emily's face had to be perfectly superimposed on top of real Emily's face in every video frame."


Miss Nancy ( ) posted Mon, 18 August 2008 at 10:20 PM

IMVHO the video was insufficient to see whether it were nothing but a 2008 version of canoma. 
if they're just camera-mapping a video texture onto an hi-res model and doing various photoshop
filtres, what's the point?  we might as well see the original footage.  same goes for photomanips.
I'd rather see the original photo than some quickie photoshopped thing.  maybe somebody can
post a link to one of their videos with camera and facial manipulations independent of the video
footage.



Conniekat8 ( ) posted Tue, 19 August 2008 at 12:59 AM

I forgot if it was image metrics or another outfit I saw doing this at siggraph.
They used facial expressions from a live actor to animate facial expressions on a totally different looking 3D actor. Live model was a young female. 3D model was some sort of a monster.
They were able to do it live, and save expressions for later reuse on animations.

Seems like various types of motion capture is all the rage right now. There was a milion motion capture booths at siggraph. Three or four of each doing the same thing.

Hi, my namez: "NO, Bad Kitteh, NO!"  Whaz yurs?
BadKittehCo Store  BadKittehCo Freebies and product support


SeanMartin ( ) posted Tue, 19 August 2008 at 10:46 AM

Connie, the kind of thing I think you're talking about is what they used for the facials for MONSTER HOUSE, which was pretty cool stuff.

But this? I mean, what's the point? The CG looked no better nor worse than the real person, so I wonder what they see as an advantage of this over simply filming someone. Weird.

docandraider.com -- the collected cartoons of Doc and Raider


ice-boy ( ) posted Tue, 19 August 2008 at 11:00 AM

well its cheaper if you dont need a room with 20 cameras and dots. you just need a camera and a guy in a t-shirt.


Miss Nancy ( ) posted Tue, 19 August 2008 at 4:33 PM

Attached Link: http://www.image-metrics.com/

the stuff at their website is better demo IMVHO.  tip to save more money: if they're in L.A., tell the guy with the t-shirt to turn off the air-conditioner and go topless if it gets too hot in there. :lol:



Conniekat8 ( ) posted Tue, 19 August 2008 at 7:20 PM

The point is that one can use one person for facial expressions, and a totally different figure for actual 3D model.

Like the guy that was here just last week, talked about doing some documentaries where the real person voice and image is distorted because they want to remain anonymous. Instead of using a silhouettte, he would like to use a fictional 3D character to tell the story (and show more motion then a distorted voice and a silhouette can do.)

Or one can animate a completely fictional/fantasy type figure.

Sure, it'll blur the lines of when to use a real actor vs. when to go with CG or animation even more.

Hi, my namez: "NO, Bad Kitteh, NO!"  Whaz yurs?
BadKittehCo Store  BadKittehCo Freebies and product support


Privacy Notice

This site uses cookies to deliver the best experience. Our own cookies make user accounts and other features possible. Third-party cookies are used to display relevant ads and to analyze how Renderosity is used. By using our site, you acknowledge that you have read and understood our Terms of Service, including our Cookie Policy and our Privacy Policy.