mlsanityData to 7 Oct 2026

GANSpace: Discovering Interpretable GAN Controls

arXiv 2004.02546 ↗First posted 6 Apr 2020cs.CV cs.GRcited by 612

Not on the map. Why?

Cited by 85 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. We identify important latent directions based on Principal Components Analysis (PCA) applied either in latent space or feature space. Then, we show that a large number of interpretable controls can be defined by layer-wise perturbation along the principal directions. Moreover, we show that BigGAN can be controlled with layer-wise inputs in a StyleGAN-like manner. We show results on different GANs trained on various datasets, and demonstrate good qualitative matches to edit directions found through earlier supervised approaches.

Key facts. Cited by 612 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 116; 2022: 166; 2023: 157; 2024: 95; 2025: 48; 2026: 30.

612 papers.

Sort:

By area:

  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  2. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  3. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  4. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  5. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 643
  6. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  7. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  8. 2023Zero-shot Image-to-Image Translationcited by 503
  9. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  10. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  11. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  12. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
38 more
  1. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  2. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  3. 2021GAN Inversion: A Surveycited by 366
  4. 2022Diffusion Models already have a Semantic Latent Spacecited by 324
  5. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 293
  6. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  7. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  8. 2021Improving Robustness using Generated Datacited by 233
  9. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218
  10. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  11. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  12. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  13. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Modelcited by 199
  14. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  15. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  16. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
  17. 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
  18. 2022SINE: SINgle Image Editing with Text-to-Image Diffusion Modelscited by 159
  19. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  20. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  21. 2023Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Modelscited by 148
  22. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 143
  23. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  24. 2023Generalizing Dataset Distillation via Deep Generative Priorcited by 125
  25. 2023Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometrycited by 121
  26. 2022Uncovering the Disentanglement Capability in Text-to-Image Diffusion Modelscited by 116
  27. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  28. 2021Paint by Wordcited by 107
  29. 2021One Shot Face Swapping on Megapixelscited by 105
  30. 2021Generative Models as a Data Source for Multiview Representation Learningcited by 104
  31. 2021Talk-to-Edit: Fine-Grained Facial Editing via Dialogcited by 102
  32. 2024Arc2Face: A Foundation Model for ID-Consistent Human Facescited by 101
  33. 2021Only a Matter of Style: Age Transformation Using a Style-Based Regression Modelcited by 92
  34. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  35. 2021GAN-Control: Explicitly Controllable GANscited by 91
  36. 2021Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editingcited by 91
  37. 2023Improving Tuning-Free Real Image Editing with Proximal Guidancecited by 87
  38. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85

50 most cited of 612 All 612 (JSON)