Synthetic Face
Synthetic face generation is a rapidly evolving field focused on creating realistic artificial faces for various applications, primarily driven by privacy concerns surrounding the use of real facial data in areas like face recognition. Current research emphasizes developing generative models, particularly diffusion models and GANs, that produce highly diverse and identity-consistent synthetic faces while mitigating biases and improving generalization to real-world images. This work is crucial for advancing privacy-preserving technologies in face recognition and other biometric applications, as well as providing valuable tools for studying algorithmic bias and human perception of facial features.
Papers
DigiFace-1M: 1 Million Digital Face Images for Face Recognition
Gwangbin Bae, Martin de La Gorce, Tadas Baltrusaitis, Charlie Hewitt, Dong Chen, Julien Valentin, Roberto Cipolla, Jingjing Shen
Mesh-Tension Driven Expression-Based Wrinkles for Synthetic Faces
Chirag Raman, Charlie Hewitt, Erroll Wood, Tadas Baltrusaitis