Angle Range and Identity Similarity Enhanced Gaze and Head Redirection based on Synthetic data
This work improves gaze and head redirection for applications like virtual reality or human-computer interaction, though it appears incremental as it builds on existing redirection methods with data augmentation.
The paper tackles the problem of gaze and head redirection in full-face images by addressing limitations in handling large angles and lack of training data, achieving significant improvements in redirection angular accuracy while maintaining high image quality.
In this paper, we propose a method for improving the angular accuracy and photo-reality of gaze and head redirection in full-face images. The problem with current models is that they cannot handle redirection at large angles, and this limitation mainly comes from the lack of training data. To resolve this problem, we create data augmentation by monocular 3D face reconstruction to extend the head pose and gaze range of the real data, which allows the model to handle a wider redirection range. In addition to the main focus on data augmentation, we also propose a framework with better image quality and identity preservation of unseen subjects even training with synthetic data. Experiments show that our method significantly improves redirection performance in terms of redirection angular accuracy while maintaining high image quality, especially when redirecting to large angles.