Total moving face reconstruction

Researchers Supasorn Suwajanakorn, Ira Kemelmacher-Shlizerman, and Steven M. Seitz have created tech that can take a 3D animated imprint of people’s faces from pretty much any low grade video (YouTube included). What this means for the film industry (and annoying commercials of selling vacuum cleaners) is pretty overwhelming.

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.