Moving Portraits
Communications of the ACM
Research Highlights
COVER, Sep 2014

Moving Portraits from CACM on Vimeo.

Full article text@CACM

Team:
Ira Kemelmacher-Shlizerman - University of Washington
Eli Shechtman - Adobe
Rahul Garg - Google
Steven M. Seitz - University of Washington

Technical Perspective by Alyosha Efros:  Portraiture in the Age of Big Data - Read@ACM website

"I have never been aware before how many faces there are. There are quantities of human beings, but there are many more faces, for each person has several."—Rainer Maria Rilke

Abstract: We present an approach for generating face animations from large image collections of the same person. Such collections, which we call photobios, are remarkable in that they summarize a person's life in photos; the photos sample the appearance of a person over changes in age, pose, facial expression, hairstyle, and other variations. Yet, browsing and exploring photobios is infeasible due to their large volume. By optimizing the quantity and order in which photos are displayed and cross dissolving between them, we can render smooth transitions between face pose (e.g., from frowning to smiling), and create moving portraits from collections of still photos. Used in this context, thecross dissolve produces a very strong motion effect; a key contribution of the paper is to explain this effect and analyze its operating range. We demonstrate results on a variety of datasets including time-lapse photography, personal photo collections, and images of celebrities downloaded from the Internet. Our approach is completely automatic and has been widely deployed as the "Face Movies" feature in Google's Picasa.

Bibtex:
@article{kemelmacher2014moving,
  title={Moving portraits},
  author={Kemelmacher-Shlizerman, Ira and Shechtman, Eli and Garg, Rahul and Seitz, Steven M},
  journal={Communications of the ACM},
  volume={57},
  number={9},
  pages={93--99},
  year={2014},
  publisher={ACM}
}

Contact:
Ira Kemelmacher-Shlizerman  for more information.