🧐 One paper is accepted in ICME 2022!

We first propose a mapping network to manipulate latent code which is effective for diverse situations, and design a spatial attention network to predict binary mask of certain attribute which encourages to only alter relevant region of images and suppress irrelevant changes.

In addition, we introduce a novel latent space into GAN inversion framework which achieves high reconstruction quality especially preserving identity features and retains ability to edit face attributes.

Spatial thanks to Feng Wang for model building.