3D-Faces from single Images

Schöner Milestone auf dem Weg zur One-Click-Avatar für VR/AR und natürlich, sobald die Auflösung ausreicht, für One-Click-Fakes: Ein Algorithmus, der aus LowRez-Pics dreidimensionale Gesichter errechnet. Ich hab das Demo mal mit Bildern von yours truly angetestet und die Ergebnisse sind angemessen weird.

Paper: Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression

Our CNN works with just a single 2D facial image, does not require accurate alignment nor establishes dense correspondence between images, works for arbitrary facial poses and expressions, and can be used to reconstruct the whole 3D facial geometry (including the non-visible parts of the face) bypassing the construction (during training) and fitting (during testing) of a 3D Morphable Model.

We achieve this via a simple CNN architecture that performs direct regression of a volumetric representation of the 3D facial geometry from a single 2D image. We also demonstrate how the related task of facial landmark localization can be incorporated into the proposed framework and help improve reconstruction quality, especially for the cases of large poses and facial expressions.