MaskGAN: Towards Diverse and Interactive Facial Image Manipulation

Style Copy Smiling Transfer (a) Target Image (a) Target Image (c) Modification on the mask (d) Result (c) Modification on the mask (d) Result (b) Source Image (b) Source Image Figure 1: Given a target image (a), users are allowed to modify masks of the target images in (c) according to the source images (b) so that we can obtain manipulation results (d). The left shows illustrative examples from "neutral" to "smiling", while the right shows style copy such as makeup, hair, expression, skin color, etc.