We generate face animations from large image collections of a person's face, by computing an optimized, aligned subsequence.
Our approach is the basis for the Face Movies feature in Google's Picasa.
A key contribution is proving why the cross dissolve produces a strong motion effect.
That work appeared in SIGGRAPH 2011 and was chosen to appear on the back cover!
Check out the project website for more info:
And let us know what you think! :)