OrthoGAN: Multifaceted Semantics for Disentangled Face Editing. (arXiv:2211.11825v1 [cs.CV])

This paper describes a new technique for finding disentangled semantic
directions in the latent space of StyleGAN. OrthoGAN identifies meaningful
orthogonal subspaces that allow editing of one human face attribute, while
minimizing undesired changes in other attributes. Our model is capable of
editing a single attribute in multiple directions. Resulting in a range of
possible generated images. We compare our scheme with three state-of-the-art
models and show that our method outperforms them in terms of face editing and
disentanglement capabilities. …

arxiv face semantics