Seam Manipulator: Leveraging Pixel Fusion for Depth-Adjustable Stereoscopic Image Retargeting

Abstract

To enhance the depth perception for stereoscopic image retargeting, this paper presents a depth-adjustable stereoscopic image retargeting method via pixel fusion technique. The traditional methods enforce the depth-preserving constraint on the left and right images with poor depth adaption. To solve this issue, we try to address two critical properties that how to change the widths of unmatched region to control the depth perception, and how to change the alignment of left and right seams to satisfy visual comfort limits, and thus propose a seam manipulator tool to optimize the process for scaling factor determination of stereoscopic seams. The important contribution of our method is to take scaling preservation energy and disparity consistency energy into optimization. The experimental results demonstrate that our method can achieve promising performances on depth perception and visual comfort adjustment for better visual experience.