Fast Face Image Synthesis with Minimal Training

11/05/2018
by   Sandipan Banerjee, et al.
0

We propose an algorithm to generate realistic face im-ages of both real and synthetic identities (people who donot exist) with different facial yaw, shape and resolution.The synthesized images can be used to augment datasets totrain CNNs or as massive distractor sets for biometric ver-ification experiments without any privacy concerns. Addi-tionally, law enforcement can make use of this technique totrain forensic experts to recognize faces. Our method sam-ples face components from a pool of multiple face images ofreal identities to generate the synthetic texture. Then, a real3D head model compatible to the generated texture is usedto render it under different facial yaw transformations. Weperform multiple quantitative experiments to assess the ef-fectiveness of our synthesis procedure in CNN training andits potential use to generate distractor face images. Addi-tionally, we compare our method with popular GAN modelsin terms of visual quality and execution time.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 9

research
09/07/2022

Facial De-morphing: Extracting Component Faces from a Single Morph

A face morph is created by strategically combining two or more face imag...
research
10/15/2021

On Generating Identifiable Virtual Faces

Face anonymization with generative models have become increasingly preva...
research
08/05/2022

Analyzing the Impact of Shape Context on the Face Recognition Performance of Deep Networks

In this article, we analyze how changing the underlying 3D shape of the ...
research
12/18/2020

A 3D GAN for Improved Large-pose Facial Recognition

Facial recognition using deep convolutional neural networks relies on th...
research
11/09/2021

SAFA: Structure Aware Face Animation

Recent success of generative adversarial networks (GAN) has made great p...
research
05/13/2019

Robustness Analysis of Face Obscuration

Face obscuration is often needed by law enforcement or mass media outlet...
research
09/08/2020

CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis

Last-generation GAN models allow to generate synthetic images which are ...

Please sign up or login with your details

Forgot password? Click here to reset