Abstract
Image retargeting algorithms often create visually disturb- ing distortion. We introduce the property of scene consistency, which is held by images which contain no ob ject distortion and have the cor- rect ob ject depth ordering. We present two new image retargeting algo- rithms that preserve scene consistency. These algorithms make use of a user-provided relative depth map, which can be created easily using a simple GrabCut-style interface. Our algorithms generalize seam carving. We decompose the image retargeting procedure into (a) removing im- age content with minimal distortion and (b) re-arrangement of known ob jects within the scene to maximize their visibility. Our algorithms op- timize ob jectives (a) and (b) jointly. However, they differ considerably in how they achieve this. We discuss this in detail and present examples illustrating the rationale of preserving scene consistency in retargeting.