Abstract | ||
---|---|---|
This letter proposes a novel warping-based method for the content-driven retargeting of stereoscopic images. Conventional algorithms in single image retargeting generally do not consider the scene depth saliency and disparity consistency when applied independently to left and right images . Therefore, the salient region and stereoscopic correlation of independently retargeted images can become corrupted. On the other hand, the proposed algorithm retains the stereo consistency of the retargeted images by matching the vertices of the grid and preserving the correspondence between them. Vertex disparity is propagated by a GPU interpolation to construct a sparse disparity map. To improve the capability of preserving visually important regions, the sparse disparity is used in conjunction with the image gradient in a saliency map computation. The experimental results show that the proposed method retains the correct disparity, while the salient objects remain undistorted in the retargeted stereoscopic image pairs. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/LSP.2013.2252165 | IEEE Signal Process. Lett. |
Keywords | Field | DocType |
gpu interpolation,stereoscopic images,image matching,disparity consistency,salient region,retargeting,stereoscopic correlation,stereoscopic image,scene depth saliency,sparse disparity,stereo image processing,sparse disparity map,warping based method,content driven retargeting,vertex matching,correlation methods,stereo consistency,interpolation,visualization,correlation | Computer vision,Image gradient,Image warping,Pattern recognition,Stereoscopy,Salience (neuroscience),Interpolation,Seam carving,Retargeting,Artificial intelligence,Mathematics,Salient | Journal |
Volume | Issue | ISSN |
20 | 5 | 1070-9908 |
Citations | PageRank | References |
12 | 0.53 | 6 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jin Woo Yoo | 1 | 32 | 1.78 |
Sehoon Yea | 2 | 324 | 23.44 |
In Kyu Park | 3 | 316 | 35.97 |