User Controllable Content Retargeting and Depth Adaptation for Stereoscopic Display

Abstract

This paper presents a content retargeting and depth adaptation method for the stereoscopic image. Our method allows the user to specify the retargeting scenarios to enhance the user's visual experience. Toward this end, we proposed a warping framework that takes content retargeting, depth adaptation, and interactive editing into account simultaneously for stereoscopic images. From the viewpoint of accuracy, comfortability, and controllability, we exploit the complementary relationship among image quality, depth quality, and important content and propose a grid optimization framework to fuse the three indictors. The experimental results demonstrate that our method achieves a preferable tradeoff among accuracy, comfortability, and controllability of information presentation in retargeting, obtaining satisfactory visual experience for users.