Gallery Update

Jaco sent us the following images of reconstructions he did in past few days: His family, a spinning chair (animated Gif when clicked) and himself.

Creative Commons LicenseThis work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

ReconstructMe 0.4.0-218 Released

Support for custom volume sizes and other settings has been added. Here’s the complete changelog:

  • Added support for custom volume sizes and other settings.
  • Added an initial set of configuration files.
  • Dropped –highres support in favor of custom configuration files.
  • Added support for depth-only cameras such as Asus Xtion Pro.
  • This version breaks support for previously recorded streams.
  • Various fixes to reconstruction engine applied.

http://reconstructme.net/downloads/

Make sure to read the updated usage

http://reconstructme.net/usage/

Happy reconstruction!

Another Set of Scans

Mattia sent us the following beautiful collection of 3d scans he made. Click on a thumbnail to enlarge.

Creative Commons LicenseThis work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

ReconstructMe 0.4.0-193 released

Mostly a bug-fix release with the following changes

  • Added support for selecting a specific sensor using the --sensor switch. See usage for details.
  • Fixed Tripcount unknown issue.
  • Fixed Cannot find XML file issue.

Go get it here

http://reconstructme.net/downloads/


In case you want to test the Microsoft Kinect Sensor backend, read this thread

https://groups.google.com/d/topic/reconstructme/gYeH8qq0lb8/discussion

Incredible Scan of a Fiat 500C

MagWeb provides us the following incredible scan of a Fiat 500C, stitched and fusioned from 33 volumes.

Besides ReconstructMe, MagWeb uses DAVID for stitching and fusioning the volumes and Meshmixer for cleaning up. As soon as we get hold of the 3D model, we will update this post.

Creative Commons LicenseThis work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Did you know … ?

that ReconstructMe adapts itself to changing environments? We’ve put a video online to demonstrate the effects.

This video shows how ReconstructMe handles dynamic environments. It smoothly updates its state as changes occur. This allows us to put ReconstructMe to use where adaptiveness is required. Of course, these changes have to occur in a certain subset of the volume at once. You cannot change the content of the entire volume at once, or tracking failure detection will kick in.

Give it a try!

Tech Preview – Automatic Volume Stitching

The following video shows a brand new feature we’ve just added to our main development branch: Automatic Volume Stitching. In this video new volumes are created once the current volume is left. Transformations between volumes are tracked automatically and used to reconstruct a complete surface model. This will allow us to keep the volumes small and the resolution per volume high to create an accurate surface.

Note, that we haven’t applied any post-processing in Meshlab. We might add an Iterative Closest Point algorithm to increase the accuracy at volume seams, but for now, we are pretty happy with the results.

We haven’t decided when to add this feature to the public version, because more testing needs to be done before.

Happy reconstruction,
Christoph