Fake it till you make it: face analysis in the wild using synthetic data alone

By Erroll Wood, Tadas Baltruvsaitis, Charlie Hewitt, Sebastian Dziadzio, Matthew Johnson, Virginia Estellers, Thomas Joseph Cashman, Jamie Shotton. IEEE International Conference on Computer Vision, 2021

342 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/1561cdeb6dd7000f3810aabb9e6828f14799464c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Ying-Cheng Lu
  2. Tianfan Fu
  3. Huazheng Wang
  4. Wenqi Wei

In Signal Processing

  1. Wenqi Wei

Citations in the corpus