|
|
|
|
 Geometric
rearrangement of images includes operations such as image retargeting,
inpainting, or object rearrangement. Each such operation can be
characterized by a shiftmap: the relative shift of every pixel in the
output image from its source in an input image.
This operation can be described and represented as an optimal graph labeling, where
the shift-map represents the selected label for each output pixel. Two
terms are used in computing the optimal shift-map: (i) A data term which
indicates constraints such as the change in image size, object
rearrangement, a possible saliency map, etc.
(ii) A smoothness term, minimizing the new discontinuities in the output
image caused by discontinuities in the shift-map.
This graph
labeling problem can be solved using graph cuts. Since the optimization is
global and discrete, it outperforms state of the art methods in most
cases. Recent works in Image editing techniques presents efficient hierarchical solutions for
graph-cuts and operations on 1M images can take only a few seconds.
|
In this project we implemented the paper written by Yael
Pritch et al. and tried to improve
it in its weakness points.
|
|
|
|
