Editing in Style: Uncovering the Local Semantics of GANs
This addresses the need for more precise image editing in generative models, though it is incremental as it builds on existing StyleGAN capabilities.
The paper tackles the problem of limited control over GAN outputs by introducing a method for making local, semantically-aware edits to images, such as human faces and indoor scenes, using StyleGAN without external supervision, achieving both locality and photorealism in edits.
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.