News:

Rule #1 - Be Patient - Rule #2 - Don't ask when, if you don't contribute - Rule #3 - You have coding skills - LinuxMCE's small brother is available: http://www.agocontrol.com

Main Menu

Virtual 3D AI

Started by DragonK, January 13, 2012, 12:41:48 PM

Previous topic - Next topic

ardirtbiker

_if_,
  Thats kinda spooky <grin>

Dennis

_if_

@ardirtbiker: don't worry, it just takes time to find out how to make it more human and less zombie ;-)

ardirtbiker

hopefully... dont wanna get people scared!

tschak909

I don't fucking care what it is, JUST BUILD IT!

-Very Frustrated and Distressed Developer Thom


Sigg3.net

Quote from: _if_ on January 06, 2013, 02:31:47 PM
Use your imagination and let me know what you guys think.
In my imagination she's too naked :D

Great work!
But is it interface-able (like Xface) so we won't be back at the point of origin, viz. pre-recordings. It would be nice to have "it" _read_ a text-file, using Festival or something for voice, and learn it some basic mimicry based on the input.

tschak909

Make something. Make a prototype. Don't talk it to death. MAKE THE PROTOTYPE, AND TALK ABOUT THE F****** PROTOTYPE! JESUS PEOPLE, HOW MANY TIMES DO I HAVE TO REITERATE THIS?!

-Thom

_if_

@Sigg3: I had plans for that before, but it turned out to be much much more complex, and if you look at the lipsync in the videos the original poster posted - that is not even close to any real speaking even if it's done by a professional company.
Once the model is done it's not that much of effort to add new animations because all you need is new spoken text from the TTS and a camshot from my lips moving for tracking. Also, we don't have that much cases which need that much of flexibility I think. For example the Install Wizard, that is not a thing which will change every day...

@thom: I DO work on it and still I'm interested in ideas, so it's alright if you don't care but why don't you just ignore this threat instead of spaming it all the time?

thanks
IF

tschak909

Boy, understanding subtlety isn't one of your strong points, is it? :)

Ok, I will be plain. I am interested!

You're working on it! COOL! OK! UPLOAD SOMETHING THAT WE CAN FIDDLE WITH! EVEN IF IT IS NOT COMPLETE! Otherwise, it does not exist, there is no point in talking about flavored air, and therefore, you are full of shit. Don't want to be? upload something. :)

-Thom

_if_

I did upload my first try a few posts ago but I know that it is a very early stage. As soon as I have more to show I will upload it...

Sigg3.net

I guess tschak is just getting excited :D

Yeah, I checked the videos last night. The lipsync does NOT have to be "correct", only moving when there IS speaking. Add to that some prerecorded gestures (laugh, smile, whoops aso) and you have an API. Continue the good work!


hari

can you make her look like cylon six?
rock your home - [url="http://www.agocontrol.com"]http://www.agocontrol.com[/url] home automation

_if_

#27
in some years when my blenderskills have improved that may be possible...but don't forget: you can't marry a 3D model!

btw: little progress http://www.youtube.com/watch?v=bEVmxuJGlU0&feature=youtu.be

phenigma

Looking good!  Very neat stuff!

J.
My setup: [url="http://wiki.linuxmce.org/index.php/User:Phenigma"]http://wiki.linuxmce.org/index.php/User:Phenigma[/url]

_if_

as it's been a long time since the last update, I just wanted to show progress (I did not have much time so its not much).
I played with creating hair and found out that this is crazy hard to do...anyway: http://youtu.be/DUQy14fcHbQ

greetz
IF