# Navigating the GAN Parameter Space for Semantic Image Editing

arXiv: https://arxiv.org/abs/2011.13786 · HTML: https://mlsanity.com/paper/2011.13786/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 30 of 49)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation](https://mlsanity.com/paper/2209.09002/) (2022)
- [Style-Based Global Appearance Flow for Virtual Try-On](https://mlsanity.com/paper/2204.01046/) (2022)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions](https://mlsanity.com/paper/2104.00820/) (2021)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Interpreting the Weight Space of Customized Diffusion Models](https://mlsanity.com/paper/2406.09413/) (2024)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights](https://mlsanity.com/paper/2603.12228/) (2026)
- [Region-Based Semantic Factorization in GANs](https://mlsanity.com/paper/2202.09649/) (2022)
- [The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation](https://mlsanity.com/paper/2211.12347/) (2022)
- [CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation](https://mlsanity.com/paper/2210.03919/) (2022)
- [VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs](https://mlsanity.com/paper/2303.15893/) (2023)
- [UnGANable: Defending Against GAN-based Face Manipulation](https://mlsanity.com/paper/2210.00957/) (2022)
- [Synthetic Data Supervised Salient Object Detection](https://mlsanity.com/paper/2210.13835/) (2022)
- [LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis](https://mlsanity.com/paper/2301.04604/) (2023)
- [Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation](https://mlsanity.com/paper/2111.13010/) (2021)
- [GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image](https://mlsanity.com/paper/2404.02152/) (2024)
- [Latent Transformations via NeuralODEs for GAN-based Image Editing](https://mlsanity.com/paper/2111.14825/) (2021)
- [Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial Networks](https://mlsanity.com/paper/2309.14054/) (2023)
- [Exploring Gradient-based Multi-directional Controls in GANs](https://mlsanity.com/paper/2209.00698/) (2022)
- [CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Exploration](https://mlsanity.com/paper/2306.08226/) (2023)
- [Closed-Loop Unsupervised Representation Disentanglement with β-VAE Distillation and Diffusion Probabilistic Feedback](https://mlsanity.com/paper/2402.02346/) (2024)
- [IA-FaceS: A Bidirectional Method for Semantic Face Editing](https://mlsanity.com/paper/2203.13097/) (2022)
- [NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation](https://mlsanity.com/paper/2304.11342/) (2023)
- [Data Redaction from Conditional Generative Models](https://mlsanity.com/paper/2305.11351/) (2023)
- [CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimization](https://mlsanity.com/paper/2402.02313/) (2024)
- [Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability](https://mlsanity.com/paper/2207.09367/) (2022)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) are currently an indispensable tool for visual editing, being a standard component of image-to-image translation and image restoration pipelines. Furthermore, GANs are especially useful for controllable generation since their latent spaces contain a wide range of interpretable directions, well suited for semantic editing operations. By gradually changing latent codes along these directions, one can produce impressive visual effects, unattainable without GANs. In this paper, we significantly expand the range of visual effects achievable with the state-of-the-art models, like StyleGAN2. In contrast to existing works, which mostly operate by latent codes, we discover interpretable directions in the space of the generator parameters. By several simple methods, we explore this space and demonstrate that it also contains a plethora of interpretable directions, which are an excellent source of non-trivial semantic manipulations. The discovered manipulations cannot be achieved by transforming the latent codes and can be used to edit both synthetic and real images. We release our code and models and hope they will serve as a handy tool for further efforts on GAN-based image editing.