We present a method for building a
morphable face model directly from photos on the Internet.
Morphable models have shown very impressive results more
than a decade ago, one of the major challenges, however,
is to capture and register 3D laser scans of large number
of faces and facial expressions. Nowadays, there are
enormous amounts of face photos on the Internet, large
portion of which has semantic labels. We propose a
framework to build a morphable model directly from photos;
our framework includes dense registration of Internet
photos, as well as, new single
view shape reconstruction and expression modification algorithms.
keywords: single view face reconstruction, 3D, facial expression modification, facial expression reconstruction, faces, in the wild, Internet photos, computer, vision.
Spotlight Paper Video Poster
will upload soon (email me if you'd like it sooner!)
Ira Kemelmacher-Shlizerman, "Internet-based Morphable Model", International Conference on Computer Vision (ICCV), 2013.
Thanks to Supasorn Suwajanakorn for helping create the videos.