Face Synthesis

Keywords: face synthesis, face recognition, face analysis, computer graphics, data augmentation
Fall 2015 - Present
teaser image

Description

We propose an algorithm to generate realistic face images of both real and synthetic identities (people who do not exist) with different facial yaw, shape and resolution. The synthesized images can be used to augment datasets to train CNNs or as massive distractor sets for biometric verification experiments without any privacy concerns. Additionally, law enforcement and intelligence services can make use of this technique to train forensic experts to recognize faces. Our method samples face components from a pool of multiple face images of real identities to generate the synthetic texture. Then, a real 3D head model compatible to the generated texture is used to render it under different facial yaw transformations. We perform multiple quantitative experiments to assess the effectiveness of our synthesis procedure in CNN training and its potential use to generate distractor face images. Additionally, we compare our method with popular GAN models in terms of visual quality and execution time.

Hardware support was provided by the NVIDIA Corporation.

Publications

  • "Fast Training-free Face Image Synthesis,"
    Sandipan Banerjee, Walter J. Scheirer, Kevin Bowyer, Patrick Flynn,
    IEEE Winter Conference on Applications of Computer Vision (WACV),
    January 2019.
  • "SREFI: Synthesis of Realistic Example Face Images,"
    Sandipan Banerjee, John S. Bernhard, Walter J. Scheirer, Kevin Bowyer, Patrick Flynn,
    Proceedings of the IAPR/IEEE International Joint Conference on Biometrics (IJCB),
    October 2017.