-
Welcome to the Community Forums at HiveWire 3D! Please note that the user name you choose for our forum will be displayed to the public. Our store was closed as January 4, 2021. You can find HiveWire 3D and Lisa's Botanicals products, as well as many of our Contributing Artists, at Renderosity. This thread lists where many are now selling their products. Renderosity is generously putting products which were purchased at HiveWire 3D and are now sold at their store into customer accounts by gifting them. This is not an overnight process so please be patient, if you have already emailed them about this. If you have NOT emailed them, please see the 2nd post in this thread for instructions on what you need to do
facial reconstruction from skull program
- Thread starter Janet
- Start date
DanaTA
Distinguished
I think it's more complex than that. One would need a detailed knowledge of muscle structures and perhaps ethnic variations in certain areas.
Dana
True. I think it would be do-able though. I know these are supposed to be extremely expensive and the people who do them are artists in their own right. I know there's some intuition involved. There was one reconstruction where they guy that did it even guessed the type of glasses the guy would wear some years later.
But for a quick and dirty reconstruction it could work I think.
But for a quick and dirty reconstruction it could work I think.
Electro-harpist
Member
You'd first need to have a good 3D scan of a skull, and to know the time-period (e.g. 600 B.C.) and place found, and thus the likely local head-face type and facial hair arrangement and width/lengths. That's not impossible.
With those basic parameters a theoretical AI software would then 'match and tweak' based on its knowledge of a corpus of front-facing photos of existing expert reconstructions of face-skulls from the same place and time-period (e.g Iron Age Britain in 600 B.C.).
In the absence of such AI software (such does not appear to exist as a .EXE installer, at present), the best way might be to reverse the general process. Find out what a gender/age matched face of the period should look like, then broadly replicate that face in Poser or DAZ, then retro-fit its mesh back over the 3D skull and adjust to fit as you go.
With those basic parameters a theoretical AI software would then 'match and tweak' based on its knowledge of a corpus of front-facing photos of existing expert reconstructions of face-skulls from the same place and time-period (e.g Iron Age Britain in 600 B.C.).
In the absence of such AI software (such does not appear to exist as a .EXE installer, at present), the best way might be to reverse the general process. Find out what a gender/age matched face of the period should look like, then broadly replicate that face in Poser or DAZ, then retro-fit its mesh back over the 3D skull and adjust to fit as you go.
Interesting. So it wouldn't be as easy as plug and play. Still a lot of judgements need to be made.
I know I am necroposting, but I wanted to mention in regards to this - with recent developments in AI technology something like this might become much easier. There may even be something in the works in the STEM fields for use in medical and forensic fields. If I stumble upon anything of the sort I would be happy to link to it here if that is permissable.
As an interesting side note, an old movie uses the technique you are discussing to recreate a face from a skull long before this was considered science and openly accepted:
Gorky Park(1983)
It has been a long time since I saw this film (1984) but interestingly, the facial reconstruction was the part I remembered and liked the most, it was fascinating.
Gorky Park(1983)
It has been a long time since I saw this film (1984) but interestingly, the facial reconstruction was the part I remembered and liked the most, it was fascinating.