Realtime Aesthetic Image Retargeting

Abstract

Humans have always sought to achieve aesthetics in art. In this paper, we present a novel approach for retargeting images to different aspect ratios while improving the composition aesthetics of the results. A simpler computational aesthetic energy is proposed and used to drive the salient objects and prominent lines to move towards their corresponding optimal positions. A mesh-based warping scheme is presented to transform the images while protecting the visual appearance of salient objects. The objective function is quadratic and thus it can be quickly minimized by solving a sparse linear system. The retargeting results are generated in realtime while the user changes the aspect ratios of the target images. A variety of experiments have shown the applicability and effectiveness of our algorithm.