3D-Reconstruction of Faces from Youtube-Videos

Auf der European Conference on Computer Vision haben sie eine sogenannte Total Moving Face Reconstruction vorgestellt, eine Methode, um 3D-Modelle von Gesichtern aus Youtube-Videos zu generieren und sie mit Bewegungen und Mimik aus dem Clip zu synchronisieren. In harmlos ist das ein 3D-Avatar-Generator für's Oculus Rift so in circa 2 Jahren. In doof sind das dreidimensionale und begehbare 3D-Räume aus herkömmlichen Überwachungsvideos inklusive Gesichtserkennung, ohne die Cams für teuer Geld upgraden zu müssen.


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.

Total Moving Face Reconstruction (via Alex)