CCC Blog

Catalyzing the computing research community and enabling the pursuit of innovative, high-impact research.

Computing Community Consortium Blog

The goal of the Computing Community Consortium (CCC) is to catalyze the computing research community to debate longer range, more audacious research challenges; to build consensus around research visions; to evolve the most promising visions toward clearly defined initiatives; and to work with the funding organizations to move challenges and visions toward funding initiatives. The purpose of this blog is to provide a more immediate, online mechanism for dissemination of visioning concepts and community discussion/debate about them.

“Your Cool Research Videos”: Exploring Photobios

June 14th, 2011 / in videos / by Erwin Gianchandani

(This post has been updated; please scroll down for the latest.)

Back in late April, the CCC announced a call for short videos describing exciting research and results in computer science — with the goal of communicating to undergraduates what computing research is all about. Today I’m pleased to present the first of these videos — called Exploring Photobios — in what I hope will become a continuing feature on this blog.

This video comes from Steven Seitz’s group in the Graphics and Imaging Laboratory at University of Washington Computer Science & Engineering.

All of us are photographed thousands of times over our lifetimes. Taken together, these photos form a visual record for each of us. Such a visual record, which the video’s creators call a photobio, samples an individual’s appearances over time, capturing variations in facial expression, pose, hairstyle, and other variations.

Exploring Photobios presents an approach for automatically generating face animations from large photo collections of a person’s face. By optimizing the order in which photos are displayed and cross-dissolving between them, compelling animations are created (e.g., smooth transition from frowning to smiling). A key contribution of the work — to be presented at the upcoming SIGGRAPH conference in Vancouver, BC, by Ira Kemelmacher-Shlizerman, Eli Shechtman, Rahul Garg, and Seitz — is also to explain the effect of the cross-dissolve capability.

What’s more, this approach is the basis for the recently released “Face Movies” feature in Google’s Picasa 3.8 — so you can try it out on your own photos!

Check out the video after the jump (below)…

…and be sure to pass it along to your friends and colleagues.

Also, a friendly reminder that we’re looking for cool research videos like this one, so please click here to learn how you can get involved in this effort — and make $1,000 in the process!

***

Updated August 3, 2011, at 9:33am EDT: This work — including the “Face Movies” capability in Google’s Picasa — was featured last night by a local TV news station in Seattle, WA.

(Contributed by Erwin Gianchandani, CCC Director)