Dense 3D Extraction of iPhone Photos

Loading...

Sign in or sign up now!
Alert icon
Upgrade to the latest Flash Player for improved playback performance. Upgrade now or more info.
2,233
Loading...
Alert icon
Sign in or sign up now!
Alert icon

Uploaded by on Jan 18, 2011

This quick proof of concept shows the conversion of standard iPhone photos into 3D imagery using nothing but software. It was created by Urban Robotics (UR) as a quick validation of their image processing and 3D extraction software.

This demonstration uses three photos taken of a bas-relief sculpture located in the Urban Robotics front lobby. The imagery was then fed into UR's dense 3D extraction processing software, that deconstructs and extracts every pixel. Each pixel is then repositioned into 3D space resulting in a colorized point cloud that can be viewed in standard point cloud viewers.

UR's software runs across large computer clusters, enabling the ability to scale to larger sets of images. This particular example was put together in a single day's time. Some work is still needed in refining the lens modeling of the camera (which was ignored for this video) as you can see by the noticeable internal warping of the point cloud across the image space.

If you have any business-related questions on this technology, or have desire to include the ability to create 3D models from an iPhone / iPad, please feel free to contact UR directly using the email address at the end of the video.

Also, if you are a engineer/scientist skilled in the high art of multi-view geometries, 3D reconstruction and general computer vision, please note that we are actively hiring experts in the field. We'd love to hear from you.

  • likes, 0 dislikes

Link to this comment:

Share to:
see all

All Comments (0)

Sign In or Sign Up now to post a comment!
Loading...
Alert icon
0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more