Tearable Image Warping for Extreme Image Retargeting

We introduce a new image geometric transformation, named tearable image warping, for content-aware image retargeting and recomposition. In tearable image warping, an object is allowed to partially detached from the background during warping, which allows the background to warp more freely without distorting the object. The part of the object that is still attached to the background ensures that spatial semantics between the object and its environment is preserved. Compared to traditional non-homogeneous image warping, tearable warping produces retargeted results with less severe distortions, especially in cases of extreme retargeting. Compared to scene carving, tearable warping can better preserve the global context and achieve better scene consistency by preserving the semantic connectedness between an object and its environment. In addition, tearable warping is also able to alter the objectbackground relationship within the image, which makes it quite suitable for aesthetics-based image recomposition. We also show that tearable image warping is a unified approach of traditional non-homogeneous image warping and the cut-and-paste techniques.