Stereoscopic image warping for enhancing composition aesthetics

The increased popularity of stereo photography due to the availability of stereoscopic lens and cameras has aroused research interest in stereo image editing. In this paper, we present an automatic, aesthetic-based warping approach to recompose both the left and right stereo image pair simultaneously using a global optimization algorithm. To maximize image aesthetics, we minimize a set of aesthetics errors formulated based on selected photographic composition rules during the warping process. In addition, our algorithm attempts to preserve the stereoscopic properties by minimizing disparity change and vertical drift in the resulting image. Experimental results shows that our approach successfully relocate salient objects according to the selected photographic rules to enhance compositional aesthetics and maintain disparity consistency to create a comfortable 3D viewing experience.

[1]  Yun Zhang,et al.  StereoPasting: Interactive Composition in Stereoscopic Images , 2013, IEEE Transactions on Visualization and Computer Graphics.

[2]  Ligang Liu,et al.  Nonhomogeneous scaling optimization for realtime image resizing , 2010, The Visual Computer.

[3]  Shai Avidan,et al.  Geometrically consistent stereo seam carving , 2011, 2011 International Conference on Computer Vision.

[4]  Wu-chi Feng,et al.  Aesthetics-Based Stereoscopic Photo Cropping for Heterogeneous Displays , 2012, IEEE Transactions on Multimedia.

[5]  Matthias Zwicker,et al.  Stereoscopic 3D copy & paste , 2010, SIGGRAPH 2010.

[6]  Yung-Yu Chuang,et al.  Content-Aware Display Adaptation and Interactive Editing for Stereoscopic Images , 2011, IEEE Transactions on Multimedia.

[7]  Yung-Yu Chuang,et al.  Scene warping: Layer-based stereoscopic image resizing , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Jeffrey Ho,et al.  Shift-Map Based Stereo Image Retargeting with Disparity Adjustment , 2012, ACCV.

[9]  Stephen P. Boyd,et al.  Disciplined Convex Programming , 2006 .

[10]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .