Multi-operator Media Retargeting

The Interdisciplinary Center
Adobe Systems Inc.
Content aware resizing gained popularity lately and users can now choose from a battery of methods to retarget their media. However, no single retargeting operator performs well on all images and all target sizes. In a user study we conducted, we found that users prefer to combine seam carving with cropping and scaling to produce results they are satisfied with. This inspires us to propose an algorithm that combines different operators in an optimal manner. We define a resizing space as a conceptual multi-dimensional space combining several resizing operators, and show how a path in this space defines a sequence of operations to retarget media. We define a new image similarity measure, which we term Bi-Directional Warping (BDW), and use it with a dynamic programming algorithm to find an optimal path in the resizing space. In addition, we show a simple and intuitive user interface allowing users to explore the resizing space of various image sizes interactively. Using key-frames and interpolation we also extend our technique to retarget video, providing the flexibility to use the best combination of operators at different times in the sequence.
* patent pending
Supplemental PDF (20mb) Results

We thank the anonymous SIGGRAPH reviewers for their comments. We thank Maya Yaniv for narrating our video. We thank the flickr members who have kindly made their media available for research purposes via the creative commons license: Ben Harris-Roxas (fishing), danorbit (desk), david.bunting (volleyball), g_magnan (italy), Greg Gladman (church, wheels), i am indisposed (snow), iboy daniel (mnm), Pandiyan (pond), romainguy (surfers), thomas23 (glasses), van swearingen (orchid), etrusia_uk (Bodiam castle). We also thank the users of and who have shared their images through public domain (tiger, eagle, stairs, islands). The Taj Mahal image is courtesy of The San Francisco heart image and results were borrowed from [Wang et al. 2008]. The bicycle, Buddha, car, malibu, foliage, face, mochizuki, venice and waterfall images are borrowed from [Avidan and Shamir 2007]. The osaka image and highway video are taken from [Rubinstein et al. 2008]. The birds video sequence is a snipped from “for the birds”, courtesy of Disney/Pixar.