h a l f b a k e r yThe embarrassing drunkard uncle of invention.
add, search, annotate, link, view, overview, recent, by name, best, random
news, help, about, links, report a problem
browse anonymously,
or get an account
and write.
register,
|
|
|
This is a combination of two existing AI technologies.
The first one is computer vision & scene understanding. That is, if you're looking at a picture of a beach, recognize features and create a textual description such as "Three palm trees line the beachfront. The sun is 27 degrees over the horizon.
Cumulonimbus clouds are seen above horizon." The level of detail in the description can vary.
The second portion of this is is a system that has pre-defined 3D models for a lot of common things such as trees, clouds, people, etc.
The system first takes the picture, creates a textual description of it, then hands this over to the second component which tries to reconstruct it. There will, of course, be ambiguities which the second AI system will have to resolve, thus creating a photorealistic rendering that _could_ have been the original thing but is actually a re-interpretation of it.
[Think about how many different pictures there are of famous historical events]
Computational Heraldry
http://mustard.tapo.../xq/xhtml.xq?id=115
Automatic generation of coat of arms from a specialized medieval language called "blazon" [cowtamer, Apr 09 2009]
[link]
|
| |
yes, think about that. wowie! |
|
| |
The second is baked in the form Open Source 3D models and a site of the same name (which is v. slow and needs subscription hmmm). |
|
| |
The first bit is getting there so I'm not really seeing much of an idea apart from "Won't it be nice when it happens". |
|
| |
Hey, if the 2nd part is baked, I'd love to have the actual link. I've heard there's some research into it, but have not seen anything about it outside a graduate level Computational Linguistics class I took once. Parsing a sentence to create a scene is still a non-trivial AI problem as far as I know. |
|
| |
//The second portion of this is is a system that has pre-defined 3D models for a lot of common things such as trees, clouds, people, etc.// |
|
| |
Thats the second part. Google Open Source 3D models. I think you're refering to a problem with the first part which is not using a mathematical language in the firstplace e.g. palm tree at (0.71, 4.43,0.03). |
|
| |
Could be a useful bandwidth reducing tool for video, depending on the use and the extent of the object library. |
|
| |
The second part of the problem is more complicated than having an open source 3D library. It's the problem of picking the appropriate shape and deducing from the description (and the rest of the scene that has already been constructed) where it should go. The scene may have to be revised as the description is parsed. |
|
| |
Consider the simple example: |
|
| |
"The is an office chair behind the desk. The chair is red and has 6 wheels. The desk is in front of the window" |
|
| |
The system would have to deduce |
|
| |
* That the chair is between the window and the desk |
|
| |
* That the desk is probably an office desk (and not a school desk) |
|
| |
* That the setting is probably an office (as opposed to an outdoor scene) and might have other office-appropriate items |
|
| |
* That the desk has an opening where the wheels are visible to the observer ("behind" is a relative concept that has no meaning without the location of an observer) |
|
| |