Total Moving Face Reconstruction


Mon, Sep 22nd, 2014 21:06 by capnasty NEWS

The University of Washington introduces the Total Moving Face Reconstruction, a system capable of watching a video of a person's face and, frame by frame, reconstruct it in a detailed 3D model.

We present an approach that takes a single video of a person's face and reconstructs a high detail 3D shape for each video frame. We target videos taken under uncontrolled and uncalibrated imaging conditions, such as youtube videos of celebrities. In the heart of this work is a new dense 3D flow estimation method coupled with shape from shading. Unlike related works we do not assume availability of a blend shape model, nor require the person to participate in a training/capturing process. Instead we leverage the large amounts of photos that are available per individual in personal or internet photo collections. We show results for a variety of video sequences that include various lighting conditions, head poses, and facial expressions.



You may also be interested in:

StreetScore: Predicting the Perceived Safety of One Million Streetscapes
If San Francisco's Crime Were Elevations
Your Big Breakthrough Comes at Age 35
If the World's Population Lived in One City...
Let's Free Congress: Infographic-Like Website on the Impact of Donations in Government's Decisions