Fast Face Image Synthesis with Minimal Training

Abstract

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 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.

arXiv commentTo appear in IEEE WACV 2019. Get our data (2M face images of 12K synthetic subjects, 8K 3D head models) by accessing the "Notre Dame Synthetic Face Dataset" here: https://cvrl.nd.edu/projects/data/

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Learning Face Representation from Scratch
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• VGGFace2: A dataset for recognising faces across pose and age
• A Light CNN for Deep Face Representation with Noisy Labels
• Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
• Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
• CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
• MAGAN: Margin Adaptation for Generative Adversarial Networks
• Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
• Face Aging With Conditional Generative Adversarial Networks
• On Face Segmentation, Face Swapping, and Face Perception
• Recent Progress of Face Image Synthesis