Fake It Till You Make It: Face analysis in the wild using synthetic data alone

TL;DR

This paper shows that high-quality synthetic face data alone can be used to train models that perform well on real-world face analysis tasks, eliminating the need for real data.

Contribution

It introduces a method to generate highly realistic synthetic face data that generalizes to real-world datasets without domain adaptation.

Findings

Models trained on synthetic data match real data accuracy.

Synthetic data enables tasks with impossible manual labeling.

High realism and diversity in synthetic data improve generalization.

Abstract

We demonstrate that it is possible to perform face-related computer vision in the wild using synthetic data alone. The community has long enjoyed the benefits of synthesizing training data with graphics, but the domain gap between real and synthetic data has remained a problem, especially for human faces. Researchers have tried to bridge this gap with data mixing, domain adaptation, and domain-adversarial training, but we show that it is possible to synthesize data with minimal domain gap, so that models trained on synthetic data generalize to real in-the-wild datasets. We describe how to combine a procedurally-generated parametric 3D face model with a comprehensive library of hand-crafted assets to render training images with unprecedented realism and diversity. We train machine learning systems for face-related tasks such as landmark localization and face parsing, showing that synthetic data can both match real data in accuracy as well as open up new approaches where manual labelling would be impossible.