Frontal Face Generation Algorithm from Multi-view Images Based on Generative Adversarial Network

In a face, there is much information of person’s identity. Because this property, various tasks such as expression recognition, identity recognition and deepfake have been actively conducted. Most them use the exact frontal view given face. However, directions face can be observed rather than image in real situation. The profile (side view) lacks when comparing with image. Therefore, if we generate from other directions, obtain more on paper, propose combined style model based conditional generative adversarial network (cGAN) for generating multi-view images that consist characteristics not only includes around (hair beard) but also detailed areas (eye, nose, mouth).