Fake It Till You Make It: Face Analysis in the Wild Using Synthetic Data Alone

Erroll Wood, Tadas Baltrusaitis, Charlie Hewitt, Sebastian Dziadzio, Thomas J. Cashman, Jamie Shotton; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 3681-3691

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 labeling would be impossible.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wood_2021_ICCV, author = {Wood, Erroll and Baltrusaitis, Tadas and Hewitt, Charlie and Dziadzio, Sebastian and Cashman, Thomas J. and Shotton, Jamie}, title = {Fake It Till You Make It: Face Analysis in the Wild Using Synthetic Data Alone}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {3681-3691} }