mlsanityData to 7 Oct 2026

StyleGAN2 Distillation for Feed-forward Image Manipulation

arXiv 2003.03581 ↗First posted 7 Mar 2020cs.CVcited by 78

Not on the map. Why?

Abstract (arXiv)

StyleGAN2 is a state-of-the-art network in generating realistic images. Besides, it was explicitly trained to have disentangled directions in latent space, which allows efficient image manipulation by varying latent factors. Editing existing images requires embedding a given image into the latent space of StyleGAN2. Latent code optimization via backpropagation is commonly used for qualitative embedding of real world images, although it is prohibitively slow for many applications. We propose a way to distill a particular image manipulation of StyleGAN2 into image-to-image network trained in paired way. The resulting pipeline is an alternative to existing GANs, trained on unpaired data. We provide results of human faces' transformation: gender swap, aging/rejuvenation, style transfer and image morphing. We show that the quality of generation using our method is comparable to StyleGAN2 backpropagation and current state-of-the-art methods in these particular tasks.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 30; 2023: 15; 2024: 9; 2025: 6; 2026: 3.

78 papers.

Sort:

By area:

  1. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  2. 2021GAN Inversion: A Surveycited by 366
  3. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  4. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  5. 2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
  6. 2021Only a Matter of Style: Age Transformation Using a Style-Based Regression Modelcited by 92
  7. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  8. 2021A Latent Transformer for Disentangled Face Editing in Images and Videoscited by 67
  9. 2022CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIPcited by 60
  10. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  11. 2021Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigationcited by 53
  12. 2021Ensembling with Deep Generative Viewscited by 53
38 more
  1. 2023Training on Thin Air: Improve Image Classification with Generated Datacited by 50
  2. 2021BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generationcited by 47
  3. 2021PVA: Pixel-aligned Volumetric Avatarscited by 40
  4. 2024EditWorld: Simulating World Dynamics for Instruction-Following Image Editingcited by 37
  5. 2021Content-Aware GAN Compressioncited by 28
  6. 2022Temporally Consistent Semantic Video Editingcited by 28
  7. 2022Face Generation and Editing with StyleGAN: A Surveycited by 27
  8. 2022GLFF: Global and Local Feature Fusion for AI-synthesized Image Detectioncited by 25
  9. 2021Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIPcited by 21
  10. 2024AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusioncited by 21
  11. 2022Arbitrary-Scale Image Synthesiscited by 20
  12. 2022VToonify: Controllable High-Resolution Portrait Video Style Transfercited by 20
  13. 2023Debiased Fine-Tuning for Vision-language Models by Prompt Regularizationcited by 20
  14. 2023SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervisioncited by 20
  15. 2025Personalized Image Generation with Deep Generative Models: A Decade Surveycited by 20
  16. 2023StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Facescited by 19
  17. 2022Synthetic ID Card Image Generation for Improving Presentation Attack Detectioncited by 18
  18. 2021DoodleFormer: Creative Sketch Drawing with Transformerscited by 17
  19. 2022Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignmentcited by 16
  20. 2022GAN-based Facial Attribute Manipulationcited by 16
  21. 2022Editing Out-of-domain GAN Inversion via Differential Activationscited by 14
  22. 2023Robust Unsupervised StyleGAN Image Restorationcited by 14
  23. 2022StyleID: Identity Disentanglement for Anonymizing Facescited by 10
  24. 2024F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restorationcited by 10
  25. 2021GAN Cocktail: mixing GANs without dataset accesscited by 8
  26. 2023E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversioncited by 8
  27. 2024Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Methodcited by 8
  28. 2024Diffusion-based Speech Enhancement with Schr"odinger Bridge and Symmetric Noise Schedulecited by 8
  29. 2022Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editabilitycited by 7
  30. 2024Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generationcited by 7
  31. 2022DCT-Net: Domain-Calibrated Translation for Portrait Stylizationcited by 6
  32. 2025Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functionscited by 6
  33. 2022LANIT: Language-Driven Image-to-Image Translation for Unlabeled Datacited by 5
  34. 2021CAFLOW: Conditional Autoregressive Flowscited by 4
  35. 2022Unsupervised Scene Sketch to Photo Synthesiscited by 4
  36. 2023In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editingcited by 4
  37. 2023Generating Realistic Images from In-the-wild Soundscited by 4
  38. 2024Stylized Face Sketch Extraction via Generative Prior with Limited Datacited by 4

50 most cited of 78 All 78 (JSON)