2022
SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing
CVPR 2022poster
Recent studies have shown that StyleGANs provide promising prior models for downstream tasks on image synthesis and editing. However, since the latent codes of StyleGANs are designed to control global styles, it is hard to achieve a fine-grained control over synthesized images. We present SemanticSt…