Slashdot Mirror

← Back to Stories (view on slashdot.org)

Algorithm Seamlessly Patches Holes In Images

Posted by kdawson on from the mind-the-gap dept.

Beetle B. writes in with research from Carnegie Mellon demonstrating a new way to replace arbitrarily shaped blank areas in an image with portions of images from a huge catalog in a totally seamless manner. From the abstract: "In this paper we present a new image completion algorithm powered by a huge database of photographs gathered from the Web. The algorithm patches up holes in images by finding similar image regions in the database that are not only seamless but also semantically valid. Our chief insight is that while the space of images is effectively infinite, the space of semantically differentiable scenes is actually not that large. For many image completion tasks we are able to find similar scenes which contain image fragments that will convincingly complete the image. Our algorithm is entirely data-driven, requiring no annotations or labelling by the user."

2 of 198 comments (clear)

  1. Re:Immediate Application by CaptainPatent · · Score: 4, Insightful

    Unfortunately, I think this particular algorithm would need a base set of data to begin working. While I'm sure portions of this algorithm could be implemented for such an application, it seems a base set is needed in a single image, therefore a full blank screen from a dropped frame or damaged images showing bad colors would not be successfully mended.
    If, on the other hand, you were a movie producer and needed to get rid of the frame change holes after loosing the master print of a film, you perhaps would be able to use such a program to mend those holes in the upper corner.

    --
    Well, back to rejecting software patent applications.
  2. Image compression? by grimJester · · Score: 4, Insightful

    If any hole in the image can be filled with a part of another pic, can't you compress an image by replacing one piece at a time with a reference to a patch? Also, how about replacing with patches of higher resolution than the original? I realize it would all be technically lossy as hell, but the compression artifacts should not be very noticable to the human eye, right? Additionally, how about using this for movie compression? Filling in based on info from previous and next frame.

    I may have to actually RTFA this time.