Generative adversarial networks (GANs) synthesize realistic images from
random latent vectors. Although manipulating the latent vectors controls the
synthesized outputs, editing real images with GANs suffers from i)
time-consuming optimization for projecting real images to the latent vectors,
ii) or inaccurate embedding through an encoder. We propose StyleMapGAN: the
intermediate latent space has spatial dimensions, and a spatially variant
modulation replaces AdaIN. It makes the embedding through an encoder more
accurate than existing optimization-based methods while maintaining the
properties of GANs. Experimental results demonstrate that our method
significantly outperforms state-of-the-art models in various image manipulation
tasks such as local editing and image interpolation. Last but not least,
conventional editing methods on GANs are still valid on our StyleMapGAN. Source
code is available at this https URL

通过在中间的潜空间使用具有空间维度的调制替换 AdaIN，我们提出了 StyleMapGAN，它使得通过编码器的嵌入比现有基于优化方法更加准确，同时保持 GAN 的属性。实验结果表明，我们的方法在各种图像操作任务中显著优于最先进的模型。