mlsanityData to 7 Oct 2026

Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing

arXiv 2104.14754 ↗First posted 30 Apr 2021cs.CV cs.LGcited by 91

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming optimization for projecting real images to the latent vectors, ii) or inaccurate embedding through an encoder. We propose StyleMapGAN: the intermediate latent space has spatial dimensions, and a spatially variant modulation replaces AdaIN. It makes the embedding through an encoder more accurate than existing optimization-based methods while maintaining the properties of GANs. Experimental results demonstrate that our method significantly outperforms state-of-the-art models in various image manipulation tasks such as local editing and image interpolation. Last but not least, conventional editing methods on GANs are still valid on our StyleMapGAN. Source code is available at https://github.com/naver-ai/StyleMapGAN.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). Builds on 55 of its 65 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

55 of 65 references.

References · 55

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  11. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  12. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
38 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  3. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  4. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  5. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  6. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  7. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  8. 2018Which Training Methods for GANs do actually Converge?cited by 672
  9. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  10. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  11. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  12. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  13. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  14. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  15. 2016Adversarial Feature Learningcited by 350
  16. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  17. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
  18. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  19. 2019On the "steerability" of generative adversarial networkscited by 247
  20. 2019Large Scale Adversarial Representation Learningcited by 238
  21. 2016Adversarially Learned Inferencecited by 216
  22. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  23. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  24. 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
  25. 2019U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translationcited by 186
  26. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  27. 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
  28. 2020Adversarial Latent Autoencoderscited by 155
  29. 2016Invertible Conditional GANs for image editingcited by 118
  30. 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
  31. 2016Neural Photo Editing with Introspective Adversarial Networkscited by 109
  32. 2019Image Generation From Small Datasets via Batch Statistics Adaptationcited by 102
  33. 2020Transforming and Projecting Images into Class-conditional Generative Networkscited by 76
  34. 2018NSML: Meet the MLaaS platform with a real-world case studycited by 70
  35. 2018Spatial Fusion GAN for Image Synthesiscited by 68
  36. 2020Disentangled Image Generation Through Structured Noise Injectioncited by 39
  37. 2019Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Losscited by 35
  38. 2017NSML: A Machine Learning Platform That Enables You to Focus on Your Modelscited by 34

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 46; 2023: 21; 2024: 7; 2025: 7; 2026: 2.

91 papers.

Sort:

By area:

  1. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  2. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  3. 2022SINE: SINgle Image Editing with Text-to-Image Diffusion Modelscited by 159
  4. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  5. 2022Stitch it in Time: GAN-Based Facial Editing of Real Videoscited by 68
  6. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  7. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  8. 2022CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Trainingcited by 49
  9. 2021Image-Based CLIP-Guided Essence Transfercited by 39
  10. 2022Spatially-Adaptive Multilayer Selection for GAN Inversion and Editingcited by 39
  11. 2022Style Transformer for Image Inversion and Editingcited by 37
  12. 2022Controllable 3D Face Synthesis with Conditional Generative Occupancy Fieldscited by 37
38 more
  1. 2022TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editingcited by 36
  2. 2023Training-free Content Injection using h-space in Diffusion Modelscited by 36
  3. 2022Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Imagescited by 35
  4. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  5. 2022Detecting and Recovering Sequential DeepFake Manipulationcited by 34
  6. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  7. 2023Physics-Informed Computer Vision: A Review and Perspectivescited by 28
  8. 2022Region-Based Semantic Factorization in GANscited by 22
  9. 2022PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANscited by 20
  10. 2022DrawingInStyles: Portrait Image Generation and Editing with Spatially Conditioned StyleGANcited by 18
  11. 2022Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpointcited by 18
  12. 2022FEAT: Face Editing with Attentioncited by 16
  13. 2022A Style-aware Discriminator for Controllable Image Translationcited by 16
  14. 2022Feature-Style Encoder for Style-Based GAN Inversioncited by 15
  15. 2023LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesiscited by 15
  16. 2023MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detectioncited by 15
  17. 2021Barbershop: GAN-based Image Compositing using Segmentation Maskscited by 14
  18. 20233D-aware Blending with Generative NeRFscited by 13
  19. 2023RIGID: Recurrent GAN Inversion and Editing of Real Face Videoscited by 13
  20. 2021Fine-Tuning StyleGAN2 For Cartoon Face Generationcited by 12
  21. 2022HS-Diffusion: Semantic-Mixing Diffusion for Head Swappingcited by 12
  22. 2023CLIP-Guided StyleGAN Inversion for Text-Driven Real Image Editingcited by 12
  23. 2021Feature Statistics Mixing Regularization for Generative Adversarial Networkscited by 9
  24. 2023Make It So: Steering StyleGAN for Any Image Inversion and Editingcited by 9
  25. 2023Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generatorcited by 9
  26. 2022IA-FaceS: A Bidirectional Method for Semantic Face Editingcited by 8
  27. 2022Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generationcited by 8
  28. 2022IntereStyle: Encoding an Interest Region for Robust StyleGAN Inversioncited by 8
  29. 2023POCE: Pose-Controllable Expression Editingcited by 8
  30. 2021DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editingcited by 7
  31. 2022End-to-End Visual Editing with a Generatively Pre-Trained Artistcited by 7
  32. 2022Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editabilitycited by 7
  33. 2022Generator Knows What Discriminator Should Learn in Unconditional GANscited by 7
  34. 2022FurryGAN: High Quality Foreground-aware Image Synthesiscited by 6
  35. 2022XDGAN: Multi-Modal 3D Shape Generation in 2D Spacecited by 6
  36. 2023ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editingcited by 6
  37. 2024FACEMUG: A Multimodal Generative and Fusion Framework for Local Facial Editingcited by 6
  38. 2022PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generationcited by 5

50 most cited of 91 All 91 (JSON)