IntereStyle: Encoding an Interest Region for Robust StyleGAN Inversion. (arXiv:2209.10811v1 [cs.CV])

Recently, manipulation of real-world images has been highly elaborated along
with the development of Generative Adversarial Networks (GANs) and
corresponding encoders, which embed real-world images into the latent space.
However, designing encoders of GAN still remains a challenging task due to the
trade-off between distortion and perception. In this paper, we point out that
the existing encoders try to lower the distortion not only on the interest
region, e.g., human facial region but also on the uninterest region, e.g.,
background …

arxiv encoding