Regenerative Morphing

CVPR 2010


Eli Shechtman    Alex Rav-Acha    Michal Irani    Steve Seitz




Regenerative morphing results of a cloud into a face, and one flower bouquet into another. Both are fully automatic. In the first example, it is hard to define (even manually) a set of correspondences between the source images, as required by traditional morphing. The resulting morphs evolve smoothly from one source image to the other without loosing their sharp appearance. Note the non-trivial transitions: facial features (eyes,mouth) deform and merge into close-by similar cloud patterns, and similar flowers move towards each other while merging in a seamless way.




We present a new image morphing approach in which the output sequence is regenerated from small pieces of the two source (input) images. The approach does not require manual correspondence, and generates compelling results even when the images are of very different objects (e.g., a cloud and a face). We pose the morphing task as an optimization with the objective of achieving bidirectional similarity of each frame to its neighbors, and also to the source images.

The advantages of this approach are 1) it can operate fully automatically, producing effective results for many sequences (but also supports manual correspondences, when available), 2) ghosting artifacts are minimized, and 3) different parts of the scene move at different rates, yielding more interesting (and less robotic) transitions.



Demo video



Watch this demo video directly on Vimeo. If for some reason it does not play, you can try this iPhone friendly version.





  • CVPR paper
  • Supplementary video (20MB, H.264/AVC/MPEG-4). More detailed than the above demo video.
  • Poster





  • Shechtman E., Rav-Acha A., Irani M., Seitz S. Regenerative Morphing. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San-Francisco CA, June 2010.
  • Bibtex




  • elishe [at] cs [dot] washington [dot] edu