avatar generation from photograph

Question

2.33/5 (3 votes)

See more:

hello there. this question is simple and straight forward,does anyone know how to write code that generates a 3d photo realistic avatar from a 2d photograph(s) provided by the user(just like the concept in virtual relay,where such an avatar is generated from photographs provided by the user)?source code for this would be awesome.thanks.

Posted 1-Apr-12 7:37am

Member 8547508

Add a Solution

Comments

Sergey Alexandrovich Kryukov 1-Apr-12 14:41pm

This is not a simple question. However, this is an excellent, very interesting question, so I voted 5 (I really rarely do that). Is it your own idea?

However, I would say, the answer cannot be easy. I have a couple of more or less obvious ideas, I'll share them as soon as I find appropriate references and some time to post the answer. You should not help for a ready to use source code. At best, you will need to find and use some known techniques, hopefully from available libraries, but for acceptable results, some research and development will be needed -- again, at best.

--SA

Maximilien 1-Apr-12 16:47pm

look/google for "3d reconstruction from 2D images".

It's not an easy topic.

Sergey Alexandrovich Kryukov 2-Apr-12 19:28pm

Of course not. I think we can only talk about 2D avatars. For 3D, there is no enough information.
Even in computer tomography, which is based on multiple images taken at many different angles, the problem is classified as ill-posed (in the sense of Tikhonov), please see:
http://en.wikipedia.org/wiki/Ill-posed_problem

--SA

Member 8547508 6-Apr-12 9:05am

i see,but what about software like faceworx?and what about virtual relay?how do they work then?also EAsports have a feature tha enables you to create such an avatar to play with in FIFA 2012.how is the problem ill posed if working solutions already exist?i just wanted some more light shed on the subject,especially in terms of source code.thanks for taking time to read the question though.

Sergey Alexandrovich Kryukov 8-Apr-12 0:48am

Never tried, but in what sense are they 3D? Anyway, it's possible to have some simple model of a typical human head or a body and slightly adjust it according to the photograph, but you cannot consider it as a realistic model. It could work for avatars. Just one of the ideas. The others are about 2D processing... but I guess you are not interesting in those...
--SA

Member 8547508 16-Apr-12 17:36pm

they are pretty fun to work with(the 3d images being generated from the photos).finding out how to make my own software utilising the algorithms that those softwares use would be a step further into the project i'm currently working on. i have the other parts in place, but this part is proving to be quite difficult, i thought i might get some help here.(ask about the project if your interested).but you are right. the avatars generated are 3d and based on the graphics of most gaming systems,pretty standard in my opinion.they're not that bad but they are not photorealistic.however, they are realistic enough to bring about differentiation between various users.if you use the software for example, the avatar would look like you if i did,it would look like me and so on.the only setback is that, the algorithms in use can't efficiently model the hair of the user,and even if they can,it does prove to be quite a problem.oh yeah, and i am interested in 2d processing, i just thought that it would be cooler to jump ahead and exlpore 3d processing,it feels so awesome,writing code and seeing something come to life!i'm sure an adept such as yourself agrees.

Member 8547508 3-Apr-12 8:05am

i see,but what about software like faceworx?and what about virtual relay?how do they work then?also EAsports have a feature tha enables you to create such an avatar to play with in FIFA 2012.how is the problem ill posed if working solutions already exist?i just wanted some more light shed on the subject,especially in terms of source code.thanks for taking time to read the question though.

1 solution

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Sergey Alexandrovich Kryukov · Answer 1 · 2012-04-22T20:04:00

I already explained in my comments to the question that there is no enough information to build a 3D model, ill-posed problem like in tomography, etc. Even a human eye do not really reconstruct such mode. You would rather have a set of photographs at different angles. In 1999, I learned from some MetaCreation's people about their camera which used only two shorts, but one of them was made using specially structured lighting. Similar structured-lighting approach is used in some pseudo-3D detectors used to build a 3D profile of the Printed Circuit Board in electronic industry. Sorry I cannot give much more detail, but those approaches are very interesting and require very special hardware. This is an interesting article about building 3D models from photos:
http://www.pcworld.com/article/11311/build_3d_models_from_photos.html[^].

My little 2D ideas are rather trivial but seem realistic to me. First, I would recommend you to load and use Inkspace:
http://en.wikipedia.org/wiki/Inkscape[^],
http://inkscape.org/[^].

Please run it and play with it. It could be recommended as a primary tool for developing all kind of graphics for software, but not just for software. There are many different effects supplied with this wonderful vector editing tool, but I would like to bring your attention to two of them: [Main Menu] => Path => Trace Bitmap and [Main Menu] => Path => Simplify. These two effects can help to vectorize the photograph and morph it give it some cartoonish look. Note, that simplify actually enriches the image, "simplification" simply means the process reduces the number if curve's nodes, but it gives it more sophisticated look. You also can search for effects of "posterization" (elsewhere, please see http://en.wikipedia.org/wiki/Posterization[^]). As Inkscape is Open-Source software, you can locate the source code of the effects and learn how to implement them.

My other more advanced but more fuzzy idea is the generalization of posterization. In principle, it's possible to decompose an image into a set of areas characterized with some "dominating gradient". The gradient withing each area can be reconstructed by interpolation and added to the model. So, the final model of the image should present a set of areas bounded by Bezier curves with gradient fill in each of them. Some problem could be smooth stitching them on their boundaries. I feel that the most adequate approach would be… ignoring this problem. Depending on how decomposition into areas is done, this effect can create visible color boundaries between the areas, like in classical posterization. It could support cartoonish look of the image and look natural enough.

After all, the whole field of painting including portrait painting is about the play with human perception. In most graphical styles, a human head is depicting with the use of some strokes on the face, curved lines with some thickness. There are no such line in real life! Nevertheless, the artistic styles of drawing often show the lines; and human perception reconstructs 3D image of a human head from this non-existent-in-nature images.

—SA