Academy & Industry Research Collaboration Center (AIRCC)

Volume 12, Number 13, July 2022

Applied Monocular Reconstruction of Parametric Faces with Domain Engineering


Igor Borovikov, Karine Levonyan, Jon Rein, Pawel Wrotek and Nitish Victor, Electronic Arts, USA


Many modern online 3D applications and videogames rely on parametric models of human faces for creating believable avatars. However, manual reproduction of someone's facial likeness with a parametric model is difficult and time-consuming. Machine Learning solution for that task is highly desirable but is also challenging. The paper proposes a novel approach to the so-called Face-to-Parameters problem (F2P for short), aiming to reconstruct a parametric face from a single image. The proposed method utilizes synthetic data, domain decomposition, and domain adaptation for addressing multifaceted challenges in solving the F2P. The opensourced codebase illustrates our key observations and provides means for quantitative evaluation. The presented approach proves practical in an industrial application; it improves accuracy and allows for more efficient models training. The techniques have the potential to extend to other types of parametric models.


Face Reconstruction, Parametric Models, Domain Decomposition, Domain Adaptation.