Geometric rearrangement of images includes operations such as image retargeting, object removal, or object rearrangement. Each such operation can be characterized by a shift-map: the relative shift of every pixel in the output image from its source in an input image.
We describe a new representation of these operations 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. Efficient hierarchical solutions for graph-cuts are presented, and operations on 1M images can take only a few seconds.
Retargeting | Inpainting | Reshuffling | Composition |
|
More
Retargeting Examples |
@inproceedings{Shiftmap-09, title = {Shift-Map Image Editing}, author = {Y. Pritch and E. Kav-Venaki and S. Peleg}, booktitle = {ICCV'09}, month = {Sept}, year = {2009}, pages = {151--158}, address = {Kyoto} } @inproceedings{Feedback-10, title = {Feedback Retargeting}, author = {E. Kav-Venaki and S. Peleg}, booktitle = {Media Retargeting Workshop at ECCV 2010}, month = {Sept}, year = {2010}, address = {Crete} } @inproceedings{Snap-Composition-11, title = {Snap Image Composition}, author = {Y. Pritch, Y. Poleg, and S. Peleg}, booktitle = {MIRAGE 2011 (5th Int. Conf. on Computer Vision / Computer Graphics Collaboration Techniques and Applications)}, month = {October}, year = {2011}, address = {Rocquencourt, France}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, volume = {6930}, pages = {181--191} }