# SREFI: Synthesis of Realistic Example Face Images

## TL;DR

This paper introduces SREFI, a novel method for generating large sets of realistic synthetic face images to expand datasets without privacy issues, improving face recognition performance.

## Contribution

The paper presents SREFI, a new face synthesis technique capable of creating diverse, high-quality synthetic identities to enhance face recognition datasets and models.

## Key findings

- Synthetic faces are visually realistic and unique.
- Augmented datasets with synthetic faces improve CNN recognition accuracy.
- Synthetic face training boosts performance on challenging real images.

## Abstract

In this paper, we propose a novel face synthesis approach that can generate an arbitrarily large number of synthetic images of both real and synthetic identities. Thus a face image dataset can be expanded in terms of the number of identities represented and the number of images per identity using this approach, without the identity-labeling and privacy complications that come from downloading images from the web. To measure the visual fidelity and uniqueness of the synthetic face images and identities, we conducted face matching experiments with both human participants and a CNN pre-trained on a dataset of 2.6M real face images. To evaluate the stability of these synthetic faces, we trained a CNN model with an augmented dataset containing close to 200,000 synthetic faces. We used a snapshot of this trained CNN to recognize extremely challenging frontal (real) face images. Experiments showed training with the augmented faces boosted the face recognition performance of the CNN.