Total Moving Face Reconstruction [chapter]

Supasorn Suwajanakorn, Ira Kemelmacher-Shlizerman, Steven M. Seitz
2014 Lecture Notes in Computer Science  
Fig. 1 . Given a YouTube video of a person's face our method estimates high detail geometry (full 3D flow and pose) in each video frame completely automatically. Abstract. 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
more » ... 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.
doi:10.1007/978-3-319-10593-2_52 fatcat:l24mxowvqfem3g7rl7ep4cysqe