mlsanityData to 7 Oct 2026

Closed-Form Factorization of Latent Semantics in GANs

arXiv 2007.06600 ↗First posted 13 Jul 2020cs.CVcited by 407

Not on the map. Why?

Cited by 43 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In order to identify such latent dimensions for image editing, previous methods typically annotate a collection of synthesized samples and train linear classifiers in the latent space. However, they require a clear definition of the target attribute as well as the corresponding manual annotations, limiting their applications in practice. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. In particular, we take a closer look into the generation mechanism of GANs and further propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights. With a lightning-fast implementation, our approach is capable of not only finding semantically meaningful dimensions comparably to the state-of-the-art supervised methods, but also resulting in far more versatile concepts across multiple GAN models trained on a wide range of datasets.

Key facts. Cited by 407 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 83; 2022: 129; 2023: 115; 2024: 46; 2025: 17; 2026: 17.

407 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,603
  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. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  6. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  7. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  8. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  9. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  10. 2021GAN Inversion: A Surveycited by 366
  11. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuningcited by 338
  12. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 293
38 more
  1. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  2. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  3. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218
  4. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  5. 2023Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Modelscited by 203
  6. 2022Latent Image Animator: Learning to Animate Images via Latent Space Navigationcited by 172
  7. 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
  8. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  9. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  10. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 143
  11. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  12. 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 122
  13. 2023Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometrycited by 121
  14. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  15. 2022Uncovering the Disentanglement Capability in Text-to-Image Diffusion Modelscited by 116
  16. 2022Disentangled Representation Learningcited by 111
  17. 20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
  18. 2021Talk-to-Edit: Fine-Grained Facial Editing via Dialogcited by 102
  19. 2022Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesiscited by 93
  20. 2021Only a Matter of Style: Age Transformation Using a Style-Based Regression Modelcited by 92
  21. 2021Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editingcited by 91
  22. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  23. 2023VideoLCM: Video Latent Consistency Modelcited by 90
  24. 2023StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generatorcited by 89
  25. 2022Style-Based Global Appearance Flow for Virtual Try-Oncited by 88
  26. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  27. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  28. 2021CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directionscited by 78
  29. 2022Stitch it in Time: GAN-Based Facial Editing of Real Videoscited by 68
  30. 2021Controllable and Compositional Generation with Latent-Space Energy-Based Modelscited by 64
  31. 2023Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Modelscited by 60
  32. 2022StyleLight: HDR Panorama Generation for Lighting Estimation and Editingcited by 59
  33. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  34. 2024Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversioncited by 58
  35. 2021Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templatescited by 57
  36. 2021Rebooting ACGAN: Auxiliary Classifier GANs with Stable Trainingcited by 57
  37. 2021Towards Vivid and Diverse Image Colorization with Generative Color Priorcited by 55
  38. 2021GAN Inversion for Out-of-Range Images with Geometric Transformationscited by 55

50 most cited of 407 All 407 (JSON)