Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and
Original Paper: TP-GAN
Abstract
- TP-GAN simultaneously perceive global structures and local details. Four landmark located patch networks are proposed to attend to local textures in addition to the commonly used global encoder-decoder network.
- a combination of adversarial loss, symmetry loss and identity preserving loss.
Approach
denote to be frontal face image, and to be profile face image. The author feed the network with pairs of corresponding { } from multiple identities y.