mlsanityData to 14 Oct 2026

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

arXiv 1703.06868 ↗First posted 20 Mar 2017cs.CVcited by 2,010

Not on the map. Why?

Cited by 212 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles. In addition, our approach allows flexible user controls such as content-style trade-off, style interpolation, color & spatial controls, all using a single feed-forward neural network.

Key facts. Cited by 2,010 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 388; 2022: 394; 2023: 409; 2024: 330; 2025: 302; 2026: 187.

2,010 papers.

Sort:

By area:

  1. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  2. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  3. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  4. 2021Domain Generalization: A Surveycited by 764
  5. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  6. 2021Domain Generalization with MixStylecited by 566
  7. 2021Neural Fields in Visual Computing and Beyondcited by 540
  8. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  9. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  10. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  11. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 408
  12. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
38 more
  1. 2021GAN Inversion: A Surveycited by 367
  2. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  3. 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 334
  4. 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 303
  5. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 294
  6. 2022Inversion-Based Style Transfer with Diffusion Modelscited by 291
  7. 2021VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalizationcited by 287
  8. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  9. 2023Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translationcited by 253
  10. 2021SimSwap: An Efficient Framework For High Fidelity Face Swappingcited by 243
  11. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 237
  12. 2022BBDM: Image-to-image Translation with Brownian Bridge Diffusion Modelscited by 225
  13. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 220
  14. 2023Style Aligned Image Generation via Shared Attentioncited by 216
  15. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 212
  16. 2021PIRenderer: Controllable Portrait Image Generation via Semantic Neural Renderingcited by 203
  17. 2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
  18. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  19. 2023Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfercited by 196
  20. 2023ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAscited by 194
  21. 2021StyTr2: Image Style Transfer with Transformerscited by 187
  22. 2023CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Priorcited by 184
  23. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 180
  24. 2021AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfercited by 178
  25. 2022Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 178
  26. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  27. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  28. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  29. 2023GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latentscited by 158
  30. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Modelscited by 155
  31. 2024Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generationcited by 155
  32. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 153
  33. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 152
  34. 2022EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Modelcited by 151
  35. 2022Diffusion-based Image Translation using Disentangled Style and Content Representationcited by 149
  36. 2022ARF: Artistic Radiance Fieldscited by 147
  37. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  38. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140

50 most cited of 2,010 All 2,010 (JSON)