Editing in Style: Uncovering the Local Semantics of GANs

2020/04/29 by Edo Collins, Raja Bala, Collins, Edo +5 · 3 citations
Computer Science · #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2004.14367

openalex publication_date 2020/04/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Generative Adversarial Networks: An Overview
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Towards a Definition of Disentangled Representations
• Interpreting the Latent Space of GANs for Semantic Face Editing

Cited by

• A Turn Toward Better Alignment: Few-Shot Generative Adaptation with Equivariant Feature Rotation
• Learning Common and Salient Generative Factors Between Two Image Datasets
• LoRAverse: A Submodular Framework to Retrieve Diverse Adapters for Diffusion Models

Related

• Navigating the GAN Parameter Space for Semantic Image Editing
• SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing
• Discovering Class-Specific GAN Controls for Semantic Image Synthesis
• Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators?
• InvGAN: Invertible GANs