[alicebot-archcomm] RE: [alicebot-general] 3D FACEs

Conan Callen alicebot-archcomm@list.alicebot.org
Sun, 18 Nov 2001 11:46:02 -0800 (PST)


I agree with Kims idea below.

The AIML spec should define how different
systems like facial sythesis can be access via a consistant interface and
how the client can inform the server of its requirements & capibilities.
The reference model (Alice) would then implement these interfaces and the
drivers for a selection of facial experession engines, to demonstrate how
to build new drivers (integrate a new engine).

An extension like this would allow Alice to work with many engines (a driver would need to be built for each
engine) rather then be hard coded to work with just one. For instance,
mpeg 7 allows for the embeding commands within a media
stream that will tell a synthetic face to move with the sound. I
researched using mpeg 7 in a talking head system back in '98 but
scrapped it because everything in the spec appeared to be patented.

Embedded commands:
The commands could be embedded into the aiml template. A whole new set of
tags would be required for systems that require facial expressions, but
would be stripped out before sending the text over the wire (for clients
that did not have facial support. Tonal inflections is another area that
has come up, that has the same kind of temporal issues.

There are several kinds of facial systems, from simple flipping of bit
maps of a whole face to breaking the face into regions and
coriographing all these regions to simulate complex facial expression.
Some even go as far ss to identify the muscules in the face, the direction
of pull and assoicated emotions that control them. It would be nice to
allow the client designer to chose the level of support and report that
back to the serve, who would somehow determine the correct tags to send
back to the client (or filter out the non-required tags).

This wide range of variation would indicate the need for different levels
of facial synthesis, and a protocol that would allow the client to send back
its requirements & capiblities to the server at connection time.

Conan

> Jup, I've read all the posts :)
>
> I have no precise idea on how the setup could be, but I was thinking about
> some general 3d-interface to Alicebot where the developers could import
> their own 3d-models and make it free software, and obviously somehow easy to
> use & customize..
>
>
>
> -----Original Message-----
> From: alicebot-general-admin@list.alicebot.org
> [mailto:alicebot-general-admin@list.alicebot.org]On Behalf Of Dr.
> Richard S. Wallace
> Sent: 17. november 2001 20:18
> To: alicebot-general@list.alicebot.org
> Subject: Re: [alicebot-general] 3D FACEs
>
>
> "Kim Chr. Hvidkjaer" wrote:
>
> > Thanks..
> >
> > Actually the reason why I asked is because the company I work in are doing
> a
> > lot of realtime 3d for web-use, and I think we can get them to help us
> out..
> > I've suggested it to the list once earlier, but noone seemed to comment on
> > it?
>
> Better read the archives.
>
> The most important thing is, it is not free software or open source.
>
> Rich
>
> _______________________________________________
> alicebot-general mailing list
> alicebot-general@list.alicebot.org
> UNSUBSCRIBE FROM HERE:
> http://list.alicebot.org/mailman/listinfo.cgi/alicebot-general
>
> _______________________________________________
> alicebot-general mailing list
> alicebot-general@list.alicebot.org
> UNSUBSCRIBE FROM HERE: http://list.alicebot.org/mailman/listinfo.cgi/alicebot-general
>