Editing in Style: Uncovering the Local Semantics of GANs

While the quality of GAN image synthesis has improved tremendously in recent years, our ability to control and condition the output is still limited. Focusing on StyleGAN, we introduce a simple and effective method for making local, semantically-aware edits to a target output image. This is accomplished by borrowing elements from a source image, also a GAN output, via a novel manipulation of style vectors. Our method requires neither supervision from an external model, nor involves complex spatial morphing operations. Instead, it relies on the emergent disentanglement of semantic objects that is learned by StyleGAN during its training. Semantic editing is demonstrated on GANs producing human faces, indoor scenes, cats, and cars. We measure the locality and photorealism of the edits produced by our method, and find that it accomplishes both.

Published in:
[Proceeedings of CVPR 2020]
Presented at:
IEEE Conference on Computer Vision and Patten Recognition (CVPR 2020), Virtual Conference, June 16-18, 2020
Additional link:

Note: The status of this file is: Anyone

 Record created 2020-08-11, last modified 2020-08-12

Download fulltext

Rate this document:

Rate this document:
(Not yet reviewed)