Abstract

We present an approach that takes a single video of a per- son’s face and reconstructs a high detail 3D shape for each video frame. We target videos taken under uncontrolled and uncalibrated imaging con- ditions, such as youtube videos of celebrities. In the heart of this work is a new dense 3D flow estimation method coupled with shape from shad- ing. Unlike related works we do not assume availability of a blend shape model, nor require the person to participate in a training/capturing pro- cess. 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.