Steve, thanks again! And that's spot on.for I hoped existed but are
heartened that it'll be any month or year. that's reely cool. Love reading
about the cross section of Ai and 3D work for that!
Do they even bother with projection maps and UV mapping? Just from what
i've read that's a GD nightmare to make neural nets try to do. This mere
mortal being a novice, at best, to 3D as art finds it nightmare. IIR Nvidia
was working on Deep Learning, and Super Sampling so that it's Ai projects
could have a ton of visual references for things with a objectness...ie if
a door looked like it was a door it had no problem, but the instant the
images were at all lower quality (or just low polly) it'd fail. For some
reason humans can  do that better.
Any ideas why? just humans have a bunch of experience? Where if I look at
beer I go ooh yummy incoming, is it as simple as even the best neural
networks look at a cylinder and ask: what the--- is that?
I wonder how it handles odd things. Like a humanoid object that's
especially muscular. Does  guess what the back and sides would look like?


On Wed, Oct 5, 2022 at 1:56 AM Gillian Densmore <gil.densm...@gmail.com>
wrote:

> 😍👍🖖😮😍👍🖖😍😍😍😍😍🖖😍🖖🖖😍🖖😍🖖😍😍😍😍
>
> On Tue, Oct 4, 2022 at 9:11 PM Stephen Guerin <stephen.gue...@simtable.com>
> wrote:
>
>> Gil,
>>
>> in response to your desire to generate 3D from 2D
>>
>> I've been watching the "novel view synthesis" space using NeRF (
>> https://www.matthewtancik.com/NERF) over the last 2 years or so. It was
>> close but not exactly what you were asking for. now here's a diffusion
>> approach to generate 3D from 2D.
>> https://3d-diffusion.github.io/
>>
>> On Mon, Sep 19, 2022, 3:54 PM Gillian Densmore <gil.densm...@gmail.com>
>> wrote:
>>
>>> Complexity and what's right up peoples ally:
>>>
>>> I've gotten into sketching again. Ok that's nice you'll say. and what's
>>> have to do with a list about math you say? the fun of x z, and wtf axis!
>>> Is their a program where you can sketch stuff, and it' can figure out
>>> how to make what you have drawn into something 3D enough to chunk into
>>> artstation or other places to show off? or is this where someone first
>>> laughs, then says: you poor, inocent person, that's funny. let me sas out
>>> how wicked hard that would be!
>>> -. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
>>> FRIAM Applied Complexity Group listserv
>>> Fridays 9a-12p Friday St. Johns Cafe   /   Thursdays 9a-12p Zoom
>>> https://bit.ly/virtualfriam
>>> to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>>> FRIAM-COMIC http://friam-comic.blogspot.com/
>>> archives:  5/2017 thru present
>>> https://redfish.com/pipermail/friam_redfish.com/
>>>   1/2003 thru 6/2021  http://friam.383.s1.nabble.com/
>>>
>> -. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
>> FRIAM Applied Complexity Group listserv
>> Fridays 9a-12p Friday St. Johns Cafe   /   Thursdays 9a-12p Zoom
>> https://bit.ly/virtualfriam
>> to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>> FRIAM-COMIC http://friam-comic.blogspot.com/
>> archives:  5/2017 thru present
>> https://redfish.com/pipermail/friam_redfish.com/
>>   1/2003 thru 6/2021  http://friam.383.s1.nabble.com/
>>
>
-. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe   /   Thursdays 9a-12p Zoom 
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives:  5/2017 thru present https://redfish.com/pipermail/friam_redfish.com/
  1/2003 thru 6/2021  http://friam.383.s1.nabble.com/

Reply via email to