Applied monocular reconstruction of parametric faces with domain engineering
This addresses the difficulty of manually creating believable avatars in online 3D applications and videogames, offering a practical machine learning solution.
The paper tackles the Face-to-Parameters problem by reconstructing a parametric face from a single image using synthetic data and domain engineering, improving accuracy and enabling more efficient model training for industrial applications.
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 open-sourced 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.