paper reading: TP-GAN

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 $I^F$ to be frontal face image, and $I^P$ to be profile face image. The author feed the network with pairs of corresponding {$I^F,I^P$} from multiple identities y.