- publication
- EUROGRAPHICS Symposium on Rendering 2006
- authors
- Ran Gal, Olga Sorkine-Hornung, Daniel Cohen-Or
Feature-preserving image retargeting. The mapping preserves the shape of the features at the expense of the background. Left: input image and its feature mask. Middle: feature-aware vertical stretch to 200% of the original height. Right: underlying deformation grid.
abstract
We present a method for inhomogeneous 2D texture mapping guided by a feature mask, that preserves some regions of the image, such as foreground objects or other prominent parts. The method is able to arbitrarily warp a given image while preserving the shape of its features by constraining their deformation to be a similarity transformation. In particular, our method allows global or local changes to the aspect ratio of the texture without causing undesirable shearing to the features. The algorithmic core of our method is a particular formulation of the Laplacian editing technique, suited to accommodate similarity constraints on parts of the domain. The method is useful in digital imaging, texture design and any other applications involving image warping, where parts of the image have high familiarity and should retain their shape after modification.
downloads
- Paper (EGSR 2006, official version available at http://diglib.eg.org/)
- BibTex entry
- Video
accompanying video (with narration)
hindsight
This technique turned out to be instrumental in content-aware image retargeting and other image and video processing applications that can benefit from variational image warping. See Visual Media Retargeting, SIGGRAPH ASIA 2009 course.
acknowledgments
The oil painting "End of a storm" is courtesy of Samuel Simoes. The stars and shells wallpapers are courtesy ofWallpaper Borders R Us. This work was supported in part by a grant from the Israeli Ministry of Science.