mlsanityData to 7 Oct 2026

Region-Based Semantic Factorization in GANs

arXiv 2202.09649 ↗First posted 19 Feb 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Despite the rapid advancement of semantic discovery in the latent space of Generative Adversarial Networks (GANs), existing approaches either are limited to finding global attributes or rely on a number of segmentation masks to identify local attributes. In this work, we present a highly efficient algorithm to factorize the latent semantics learned by GANs concerning an arbitrary image region. Concretely, we revisit the task of local manipulation with pre-trained GANs and formulate region-based semantic discovery as a dual optimization problem. Through an appropriately defined generalized Rayleigh quotient, we manage to solve such a problem without any annotations or training. Experimental results on various state-of-the-art GAN models demonstrate the effectiveness of our approach, as well as its superiority over prior arts regarding precise control, region robustness, speed of implementation, and simplicity of use.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 44 of its 53 references that are in the map. First posted on arXiv 19 Feb 2022.

Builds on

44 of 53 references.

References · 44

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  5. 2021Convex optimizationcited by 2,479
  6. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  8. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  9. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  10. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  11. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  12. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
32 more
  1. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  2. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  3. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  4. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  5. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  6. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
  7. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
  8. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  9. 2019On the "steerability" of generative adversarial networkscited by 247
  10. 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
  11. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  12. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  13. 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
  14. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  15. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  16. 2019Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesiscited by 106
  17. 2020Rewriting a Deep Generative Modelcited by 105
  18. 2020Controlling generative models with continuous factors of variationscited by 93
  19. 2021Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editingcited by 91
  20. 2020Generative Hierarchical Features from Synthesizing Imagescited by 83
  21. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  22. 2021Data-Efficient Instance Generation from Instance Discriminationcited by 58
  23. 2021Low-Rank Subspaces in GANscited by 52
  24. 2020Navigating the GAN Parameter Space for Semantic Image Editingcited by 49
  25. 2020GAN "Steerability" without optimizationcited by 48
  26. 2020Improving the Fairness of Deep Generative Models without Retrainingcited by 46
  27. 2019Eigenvalue and Generalized Eigenvalue Problems: Tutorialcited by 45
  28. 2021The Geometry of Deep Generative Image Models and its Applicationscited by 34
  29. 2021EigenGAN: Layer-Wise Eigen-Learning for GANscited by 34
  30. 2018A Spectral Regularizer for Unsupervised Disentanglementcited by 30
  31. 2018Spatially Controllable Image Synthesis with Internal Representation Collagingcited by 23
  32. 2021Decorating Your Own Bedroom: Locally Controlling Image Generation with Generative Adversarial Networkscited by 8

Built on by

Cited by year

Citing papers per year: 2022: 9; 2023: 8; 2024: 3; 2025: 2.

22 papers.

Sort:

By area:

  1. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  2. 2022BlobGAN: Spatially Disentangled Scene Representationscited by 35
  3. 2022High-fidelity GAN Inversion with Padding Spacecited by 23
  4. 2022PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANscited by 20
  5. 2023Latent Traversals in Generative Models as Potential Flowscited by 17
  6. 2023LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesiscited by 15
  7. 2023Exploring Sparse MoE in GANs for Text-conditioned Image Synthesiscited by 13
  8. 2023Flow Factorized Representation Learningcited by 11
  9. 2022IA-FaceS: A Bidirectional Method for Semantic Face Editingcited by 8
  10. 2022Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generationcited by 8
  11. 2022Orthogonal SVD Covariance Conditioning and Latent Disentanglementcited by 5
  12. 2023Householder Projector for Unsupervised Latent Semantics Discoverycited by 5
10 more
  1. 2023In-Domain GAN Inversion for Faithful Reconstruction and Editabilitycited by 5
  2. 2025Image Interpolation with Score-based Riemannian Metrics of Diffusion Modelscited by 4
  3. 2022Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Modelcited by 3
  4. 2024Enabling Local Editing in Diffusion Models by Joint and Individual Component Analysiscited by 3
  5. 2023Spatial Steerability of GANs via Self-Supervision from Discriminatorcited by 2
  6. 2024Revealing Directions for Text-guided 3D Face Editingcited by 2
  7. 2024Unsupervised Representation Learning from Sparse Transformation Analysiscited by 2
  8. 2022Interpreting Class Conditional GANs with Channel Awarenesscited by 1
  9. 2022Discovering Class-Specific GAN Controls for Semantic Image Synthesiscited by 1
  10. 2025UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANscited by 0