Wednesday 20 March 2013

Converting a video into a 3D mesh and reconstructing a face


The technology of SfM allow you convert, with great precision and quality, some photos into a 3D mesh.

The problem is when you don't have the photos and need to find other ways to reconstruct an object.

Fortunatelly, the Python Photogrammetry Toolbox (SfM) works well in a couple of possibilities, and like you saw in the video above, also with this type of media.


The video downloaded, shows the Budapest Múmia Projekt of the Szépművészeti Múzeum.

This project was a multidisciplinary effort not only to reconstruct the face of the mummies, but the panorama of their past lifes too.

To put the object in the scale, I use other video that show the CT-Scan with a scale at side.

Even working with a low quality reconstructed mesh, the result of the reconstruction was relatively compatible with the oficial bust made by Dr. Kustár Ágnes.

If you wanna see the step-by-step of the process, I created an album and shared it here: https://plus.google.com/photos/115430171389306289690/albums/5856903432134303473

I hope you enjoy.

A big hug and I see you in the next!




4 comments:

  1. Great Cicero. Once again, another killer video! Maybe you can also use this approach to reconstruct old buildings using old films.

    I just didn't understand a thing. In theory doesn't PPT Bundler require, for each image, the respective metadata, with camera specs (aperture, camera model)? How PPT processed the images if they are just video snapshots and not the original camera stills (snapshots don't have metadata)?

    Keep the good work

    rgaidao

    ReplyDelete
    Replies
    1. Hi rgaidao!

      Luca answered :). So thank you for the words. I think it possible use the PPT with an help of a manual reconstruction. A big hug!

      Delete
  2. Hi Ricardo,
    this was one of the things I wanted to experiment. A friend of mine gave me, some years ago, an old movie of Iraq monuments to do such a test. The problem is tat I found out that the movie had some restrictive copyright (from the American Museum which houses the original video), so I did not tried... What I am wondering is if a 3D model coming from a copyrighted video is a derivative work or has to be considered something new. Maybe it is time to write to the Museum to ask if they allow me to do the test and report the results on ATOR...

    ReplyDelete
  3. Next 12 years...for me to learn this much...I think yeah...only real things i could grasp for me was Meshlab..i am newbie in blender....

    ReplyDelete

BlogItalia - La directory italiana dei blog Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.