“Physical simulation for real-time image/video retargeting” by Gallea, Ardizzone and Pirrone

Retargeting methods present content on arbitrary aspect ratio media displays limiting distortions in relevant objects. This is done by means of applying non-homogeneous resizing operators across the whole media, constraining it to fit into the required size. Several succesful systems have been proposed to achieve image retargeting, while video retargeting is still challenging due to time consistency and computational complexity requirements. Two important contributes were proposed: non-homogeneous retargeting [Wolf et al. 2007] and improved seam-carving [Rubinstein et al. 2008]. The first one claims to achieve real-time performance but considers spatial coordinates separately. The latter do preserve media structure, but sometimes introduces artifacts and does not provide real-time performance. In addition it is not designed for streaming purposes. We show how a physical simulation solves the retargeting problem and the relative issues, such as time consistence, reporting how this is feasible in real-time. Moreover, at each step the system considers only two consequent frames, being able to deal with streaming media.

1. Cheng, M.-M., Zhang, G.-X., Mitra, N. J., Huang, X., and Hu, S.-M. 2011. Global contrast based salient region detection. In IEEE CVPR, 409–416.
2. Rubinstein, M., Shamir, A., and Avidan, S. 2008. Improved seam carving for video retargeting. ACM Transactions on Graphics (SIGGRAPH) 27, 3, 1–9.
3. Wolf, L., Guttmann, M., and Cohen-Or, D. 2007. Non-homogeneous content-driven video-retargeting. In Proceedings of the Eleventh IEEE International Conference on Computer Vision (ICCV-07).