mlsanityData to 7 Oct 2026

High-Fidelity GAN Inversion for Image Attribute Editing

arXiv 2109.06590 ↗First posted 14 Sep 2021cs.CVcited by 197

Not on the map. Why?

Cited by 32 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a novel high-fidelity generative adversarial network (GAN) inversion framework that enables attribute editing with image-specific details well-preserved (e.g., background, appearance, and illumination). We first analyze the challenges of high-fidelity GAN inversion from the perspective of lossy data compression. With a low bit-rate latent code, previous works have difficulties in preserving high-fidelity details in reconstructed and edited images. Increasing the size of a latent code can improve the accuracy of GAN inversion but at the cost of inferior editability. To improve image fidelity without compromising editability, we propose a distortion consultation approach that employs a distortion map as a reference for high-fidelity reconstruction. In the distortion consultation inversion (DCI), the distortion map is first projected to a high-rate latent map, which then complements the basic low-rate latent code with more details via consultation fusion. To achieve high-fidelity editing, we propose an adaptive distortion alignment (ADA) module with a self-supervised training scheme, which bridges the gap between the edited and inversion images. Extensive experiments in the face and car domains show a clear improvement in both inversion and editing quality.

Key facts. Cited by 197 papers in the map (data through 7 Oct 2026). Builds on 43 of its 51 references that are in the map. First posted on arXiv 14 Sep 2021.

Builds on

43 of 51 references.

References · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  8. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  9. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  10. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  11. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  12. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
31 more
  1. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  2. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  3. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  4. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 494
  5. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  6. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  7. 2021GAN Inversion: A Surveycited by 366
  8. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  9. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  10. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  11. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  12. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 333
  13. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
  14. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
  15. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  16. 2019On the "steerability" of generative adversarial networkscited by 247
  17. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  18. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  19. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  20. 2020Progressive Semantic-Aware Style Transformation for Blind Face Restorationcited by 99
  21. 2020Controlling generative models with continuous factors of variationscited by 93
  22. 2020Improved StyleGAN Embedding: Where are the Good Latents?cited by 88
  23. 2020Generative Hierarchical Features from Synthesizing Imagescited by 83
  24. 2020Transforming and Projecting Images into Class-conditional Generative Networkscited by 76
  25. 2020Collaborative Learning for Faster StyleGAN Embeddingcited by 65
  26. 2021GAN Inversion for Out-of-Range Images with Geometric Transformationscited by 55
  27. 2021Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigationcited by 53
  28. 2021LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directionscited by 52
  29. 2021Dual-Camera Super-Resolution with Aligned Attention Modulescited by 33
  30. 2021Internal Video Inpainting by Implicit Long-range Propagationcited by 19
  31. 2020Unsupervised Discovery of Disentangled Manifolds in GANscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 49; 2023: 74; 2024: 40; 2025: 20; 2026: 8.

197 papers.

Sort:

By area:

  1. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  2. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
  3. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 643
  4. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  5. 2023ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generationcited by 414
  6. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  7. 2023P+: Extended Textual Conditioning in Text-to-Image Generationcited by 242
  8. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  9. 2022Re-Imagen: Retrieval-Augmented Text-to-Image Generatorcited by 208
  10. 2023Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Modelscited by 203
  11. 2023TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Compositioncited by 182
  12. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
38 more
  1. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  2. 2022Pretraining is All You Need for Image-to-Image Translationcited by 160
  3. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 143
  4. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  5. 2023Generalizing Dataset Distillation via Deep Generative Priorcited by 125
  6. 2021FENeRF: Face Editing in Neural Radiance Fieldscited by 112
  7. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  8. 2024Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyondcited by 111
  9. 2022VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wildcited by 106
  10. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  11. 2023Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Modelscited by 85
  12. 2023Low-Light Image Enhancement via Structure Modeling and Guidancecited by 78
  13. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  14. 2022Fine-Grained Face Swapping via Regional GAN Inversioncited by 67
  15. 2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
  16. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  17. 2023Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priorscited by 64
  18. 2022StyleLight: HDR Panorama Generation for Lighting Estimation and Editingcited by 59
  19. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  20. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
  21. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  22. 2023HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Facescited by 48
  23. 2023On Exact Inversion of DPM-Solverscited by 47
  24. 2023StyleGAN knows Normal, Depth, Albedo, and Morecited by 44
  25. 2021Image-Based CLIP-Guided Essence Transfercited by 39
  26. 20223D GAN Inversion with Facial Symmetry Priorcited by 39
  27. 2023Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encodingcited by 35
  28. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  29. 2023DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protectioncited by 34
  30. 2024Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Stylecited by 33
  31. 2024RegionDrag: Fast Region-Based Image Editing with Diffusion Modelscited by 31
  32. 2023DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Modelscited by 30
  33. 2024SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusioncited by 28
  34. 2022Finding Directions in GAN's Latent Space for Neural Face Reenactmentcited by 27
  35. 2024Transferable Adversarial Facial Images for Privacy Protectioncited by 26
  36. 2022One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulationscited by 24
  37. 2022Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversioncited by 24
  38. 2023Learning Generative Structure Prior for Blind Text Image Super-resolutioncited by 24

50 most cited of 197 All 197 (JSON)