Stereo Seam Carving:
A Geometrically Consistent Approach
Tali Dekel (Basha)              Yael Moses              Shai Avidan



Image retargeting algorithms attempt to adapt the image content to the screen without distorting the important objects in the scene. Existing methods address retargeting of a single image. In this paper we propose a novel method for retargeting a pair of stereo images. Naively retargeting each image independently will distort the geometric structure and make it impossible to perceive the 3D structure of the scene. We show how to extend a single image seam carving to work on a pair of images. Our method minimizes the visual distortion in each of the images as well as the depth distortion. A key property of the proposed method is that it takes into account the visibility relations between pixels in the image pair (occluded and occluding pixels). As a result, our method guarantees, as we formally prove, that the retargeted pair is geometrically consistent with a feasible 3D scene, similar to the original one. Hence, the retargeted stereo pair can be viewed on a stereoscopic display or processed by any computer vision algorithm. We demonstrate our method on a number of challenging indoor and outdoor stereo images.
Stereo Seam Carving: A Geometrically Consistent Approach, T. Dekel (Basha), Y. Moses, and S. Avidan 
Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2013, [PDF]

"Geometrically Consistent Stereo Seam Carving ", T. Dekel (Basha), Y. Moses, and S. Avidan   
International Conference on Computer Vision 
(ICCV) 2011. Accepted as oral. [PDF]
Talk (from ICCV')

Matlab Code 
Contains pairs of stereo image + disparity maps computed by the SGM  (Semi Global Matching) algorithm. If you use these datasets in any publication, please refer to our paper. In all the datasets disparities are encoded using a scale factor -3.
This set of stereo images was downloaded from Flicker .

The images were manually rectified using  the method of Fusiello et al.

car peop;e snowman
The Middlebury stereo datasets, Aloe and Moebius.

aloe mob
This pair of stereo images is provided by Huguet et al.

Watch Our Stereo Images In 3D