notes.husk.org/likes images.

125886910456

Image 1 of 4
a-computational-approach-for-obstruction-free
Image 2 of 4
a-computational-approach-for-obstruction-free
Image 3 of 4
a-computational-approach-for-obstruction-free
Image 4 of 4
a-computational-approach-for-obstruction-free

A Computational Approach for Obstruction-Free Photography

Research from MIT CSAIL and Google have developed a way to remove foreground material such as reflections and barriers from photographs:

We present a unified computational approach for taking photos through reflecting or occluding elements such as windows and fences. Rather than capturing a single image, we instruct the user to take a short image sequence while slightly moving the camera. Differences that often exist in the relative position of the background and the obstructing elements from the camera allow us to separate them based on their motions, and to recover the desired background scene as if the visual obstructions were not there. We show results on controlled experiments and many real and practical scenarios, including shooting through reflections, fences, and raindrop-covered windows.

More Here


Date posted: 2015/08/05 00:08:57
Date liked: 2015/08/05 20:08:53
549 Tumblr notes
Liked from: prosthetic knowledge
Originally posted from: sites.google.com
Tagged:
photography 655
tech 134
reflection 32
computational photography 4
analysis 2
obstruction 1