Molding Face Shapes by Example

3D Face Reconstruction from a Single Image
using a Single Reference Face Shape

Ira Kemelmacher
Ronen Basri

Weizmann Institute of Science

Patent Pending


**** Participate in an experiment!
 "Visual similarity of face shapes" 

**** Reconstruct Your 3D Face from a photograph
        upload your image

(the result will be sent to your email)

Abstract:   Human faces are remarkably similar in global properties, including size, aspect ratio, and location of main features, but can vary considerably in details across individuals, gender, race, or due to facial expression. We propose a novel method for 3D shape recovery of faces that exploits the similarity of
faces. Our method obtains as input a single image and uses a mere single 3D reference model of a different person’s face. Classical reconstruction methods from single images, i.e. shape-from-shading, require knowledge of the reflectance properties and lighting as well as depth values for boundary
conditions. Recent methods circumvent these requirements by representing input faces as combinations (of hundreds) of stored 3D models. We propose instead to use the input image as a guide to ”mold” a single reference model to reach a reconstruction of the sought 3D shape. Our method assumes Lambertian reflectance and uses harmonic representations of lighting. It has been tested on images taken under controlled viewing conditions as well as on uncontrolled images downloaded from the internet, demonstrating its accuracy and robustness under a variety of imaging conditions and overcoming significant differences in shape between the input and reference individuals including differences in facial expressions, gender and race.

Keywords: 3D, reconstruction, single image, faces, single reference, general images, Lambertian reflectance.

ECCV'06 pdf       Journal version (email me for the preprint)      Bibtex

3D Face Reconstruction Examples:

Below are few examples. In each example, you see the input image and our reconstruction results - 3D surface (in pink) and texture. Note the specific details of the individuals (such as wrinkles on Clint Eastwood's face and smile on Tom Hanks), and also the face of Mona Lisa!


AUTHOR = {Ira Kemelmacher and Ronen Basri},
TITLE = {Molding Face Shapes by Example},
JOURNAL = {European Conf. on Computer Vision (ECCV-06), LNCS 3951},
YEAR = {2006},

Contact details:

For further details please contact: Ira Kemelmacher