Editing in Style: Uncovering the Local Semantics of GANs
arXiv:2004.14367
Abstract
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.
arXiv commentIEEE Conference on Computer Vision and Patten Recognition (CVPR), 2020. Code: https://github.com/IVRL/GANLocalEditing
References in corpus (11)
- Generative Adversarial Networks: An Overview
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Invertible Conditional GANs for image editing
- Towards a Definition of Disentangled Representations
- GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
- An Introduction to Image Synthesis with Generative Adversarial Nets
- Interpreting the Latent Space of GANs for Semantic Face Editing
- Spatially Controllable Image Synthesis with Internal Representation Collaging
- BioFaceNet: Deep Biophysical Face Image Interpretation