YesilcamGAN: Automatic face translation to Yesilcam artists
Savaş Özkan, Gözde Bozdağı Akar · 2018
In this paper, we propose a method that can automatically translate regular human faces to Yesilcam artists. Throughout the paper, two important contributions are presented. First, since a classifier based approach is used, the proposed method automatically selects the most similar artist and makes the face translation. Second, so as to obtain the latent information about faces, a pre-trained model is utilized at the encoder part. Experiments show that visual results which are perceptually promising, Yesilcam artist-like yet preserving facial features of a person, can be synthesized.