Depth-Aware Stereo Video Retargeting
Authors:
- Bing LiBLBing Li
- Chia-Wen LinCLChia-Wen Lin
- Boxin ShiBSBoxin Shi
- Tiejun HuangTHTiejun Huang
- Wen GaoWGWen Gao
- C.-C. Jay KuoCKC.-C. Jay Kuo
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6517-6525
Abstract
As compared with traditional video retargeting, stereo video retargeting poses new challenges because stereo video contains the depth information of salient objects and its time dynamics. In this work, we propose a depth-aware stereo video retargeting method by imposing the depth fidelity constraint. The proposed depth-aware retargeting method reconstructs the 3D scene to obtain the depth information of salient objects. We cast it as a constrained optimization problem, where the total cost function includes the shape, temporal and depth distortions of salient objects. As a result, the solution can preserve the shape, temporal and depth fidelity of salient objects simultaneously. It is demonstrated by experimental results that the depth-aware retargeting method achieves higher retargeting quality and provides better user experience.Keywords
This publication has 28 references indexed in Scilit:
- Display adaptive 3D content remappingComputers & Graphics, 2013
- Depth Mapping for Stereoscopic VideosInternational Journal of Computer Vision, 2012
- Enabling warping on stereoscopic imagesACM Transactions on Graphics, 2012
- Robust Image Retargeting via Axis‐Aligned DeformationComputer Graphics Forum, 2012
- Multi-perspective stereoscopy from light fieldsACM Transactions on Graphics, 2011
- Scalable and coherent video resizing with per-frame optimizationACM Transactions on Graphics, 2011
- Nonlinear disparity mapping for stereoscopic 3DACM Transactions on Graphics, 2010
- A Shape‐Preserving Approach to Image ResizingComputer Graphics Forum, 2009
- Improved seam carving for video retargetingACM Transactions on Graphics, 2008
- Seam carving for content-aware image resizingACM Transactions on Graphics, 2007