TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

Abstract

Figure 1. Diverse editing examples by TransEditor. Images on the fourth column are the sampled source images, which are semantically interpolated to the left and right sides. With our proposed dual latent spaces, namely P-space and Z-space, different attributes can be edited in one space alone or in dual spaces simultaneously, demonstrating the flexibility of our method. Head pose (the first row) and wavy hair (the second row) are edited via the P-space alone. Disentangled dual spaces enable the editing of pose and smile simultaneously (the third row) by editing pose in the P-space and smile in the Z-space. The Cross-Space Interaction allows the cooperated editing of complex attributes like gender (the last row).