mlsanityData to 7 Oct 2026

Improved StyleGAN Embedding: Where are the Good Latents?

arXiv 2012.09036 ↗First posted 13 Dec 2020cs.CV cs.GRcited by 88

Not on the map. Why?

Abstract (arXiv)

StyleGAN is able to produce photorealistic images that are almost indistinguishable from real photos. The reverse problem of finding an embedding for a given image poses a challenge. Embeddings that reconstruct an image well are not always robust to editing operations. In this paper, we address the problem of finding an embedding that both reconstructs images and also supports image editing tasks. First, we introduce a new normalized space to analyze the diversity and the quality of the reconstructed latent codes. This space can help answer the question of where good latent codes are located in latent space. Second, we propose an improved embedding algorithm using a novel regularization method based on our analysis. Finally, we analyze the quality of different embedding algorithms. We compare our results with the current state-of-the-art methods and achieve a better trade-off between reconstruction quality and editing quality.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 19; 2022: 28; 2023: 21; 2024: 16; 2025: 4.

88 papers.

Sort:

By area:

  1. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  2. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  3. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  4. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  5. 2021GAN Inversion: A Surveycited by 366
  6. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  7. 2023Break-A-Scene: Extracting Multiple Concepts from a Single Imagecited by 230
  8. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  9. 2023Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Modelscited by 203
  10. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  11. 2024ReNoise: Real Image Inversion Through Iterative Noisingcited by 127
  12. 2023Generalizing Dataset Distillation via Deep Generative Priorcited by 125
38 more
  1. 2023A Neural Space-Time Representation for Text-to-Image Personalizationcited by 123
  2. 2024Stable Flow: Vital Layers for Training-Free Image Editingcited by 111
  3. 2021Paint by Wordcited by 107
  4. 2023Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Modelscited by 98
  5. 2022Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesiscited by 93
  6. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  7. 2023Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Modelscited by 85
  8. 2021CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directionscited by 78
  9. 2021Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networkscited by 68
  10. 2022Stitch it in Time: GAN-Based Facial Editing of Real Videoscited by 68
  11. 2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
  12. 2024TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Modelscited by 64
  13. 2021GAN Inversion for Out-of-Range Images with Geometric Transformationscited by 55
  14. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  15. 2021Labels4Free: Unsupervised Segmentation using StyleGANcited by 53
  16. 2021JoJoGAN: One Shot Face Stylizationcited by 49
  17. 20223D GAN Inversion with Pose Optimizationcited by 44
  18. 2021Image-Based CLIP-Guided Essence Transfercited by 39
  19. 2022Spatially-Adaptive Multilayer Selection for GAN Inversion and Editingcited by 39
  20. 20233DAvatarGAN: Bridging Domains for Personalized Editable Avatarscited by 38
  21. 2022Style Transformer for Image Inversion and Editingcited by 37
  22. 2022TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editingcited by 36
  23. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  24. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  25. 2021StyleFusion: A Generative Model for Disentangling Spatial Segmentscited by 28
  26. 2022Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Explorationcited by 21
  27. 2025Personalized Image Generation with Deep Generative Models: A Decade Surveycited by 20
  28. 2022HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networkscited by 19
  29. 2023StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generationcited by 19
  30. 2024VRMM: A Volumetric Relightable Morphable Head Modelcited by 19
  31. 2022Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpointcited by 18
  32. 2023HairCLIPv2: Unifying Hair Editing via Proxy Feature Blendingcited by 17
  33. 2021Few-shot Image Generation with Mixup-based Distance Learningcited by 16
  34. 2022Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignmentcited by 16
  35. 2022clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIPcited by 16
  36. 2021Barbershop: GAN-based Image Compositing using Segmentation Maskscited by 14
  37. 2023Robust Unsupervised StyleGAN Image Restorationcited by 14
  38. 2024Deformable One-shot Face Stylization via DINO Semantic Guidancecited by 14

50 most cited of 88 All 88 (JSON)