mlsanityData to 7 Oct 2026

Demystifying Neural Style Transfer

arXiv 1701.01036 ↗First posted 4 Jan 2017cs.CV cs.LG cs.NEcited by 152

Not on the map. Why?

Abstract (arXiv)

Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry. Despite the amazing results, the principle of neural style transfer, especially why the Gram matrices could represent style remains unclear. In this paper, we propose a novel interpretation of neural style transfer by treating it as a domain adaptation problem. Specifically, we theoretically show that matching the Gram matrices of feature maps is equivalent to minimize the Maximum Mean Discrepancy (MMD) with the second order polynomial kernel. Thus, we argue that the essence of neural style transfer is to match the feature distributions between the style images and the generated images. To further support our standpoint, we experiment with several other distribution alignment methods, and achieve appealing results. We believe this novel interpretation connects these two important research fields, and could enlighten future researches.

Key facts. Cited by 152 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 37; 2023: 39; 2024: 25; 2025: 11; 2026: 6.

152 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2023StyleDrop: Text-to-Image Generation in Any Stylecited by 197
  3. 2021StyTr2: Image Style Transfer with Transformerscited by 186
  4. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  5. 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
  6. 2021Stylizing 3D Scene via Implicit Representation and HyperNetworkcited by 103
  7. 2022Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learningcited by 93
  8. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
  9. 2022The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matricescited by 62
  10. 2023AD-CLIP: Adapting Domains in Prompt Space Using CLIPcited by 62
  11. 2024Gramian Multimodal Representation Learning and Alignmentcited by 52
  12. 2022ArtFID: Quantitative Evaluation of Neural Style Transfercited by 49
38 more
  1. 2022Modeling Image Composition for Complex Scene Generationcited by 43
  2. 2021Rethinking Style Transfer: From Pixels to Parameterized Brushstrokescited by 42
  3. 2021Context-Aware Layout to Image Generation with Enhanced Object Appearancecited by 41
  4. 2021DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfercited by 38
  5. 2023StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalizationcited by 36
  6. 2024Customizing Text-to-Image Models with a Single Image Paircited by 36
  7. 2021Feature-based Style Randomization for Domain Generalizationcited by 34
  8. 2022Do better ImageNet classifiers assess perceptual similarity better?cited by 34
  9. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  10. 2022NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fieldscited by 33
  11. 2021Visualizing Adapted Knowledge in Domain Transfercited by 32
  12. 2025Attention Distillation: A Unified Approach to Visual Characteristics Transfercited by 32
  13. 2022FIFO: Learning Fog-invariant Features for Foggy Scene Segmentationcited by 31
  14. 2021Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolutioncited by 30
  15. 2021Style-Aware Normalized Loss for Improving Arbitrary Style Transfercited by 30
  16. 2021Aligning Correlation Information for Domain Adaptation in Action Recognitioncited by 30
  17. 2022Learning Graph Neural Networks for Image Style Transfercited by 29
  18. 2023DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matricescited by 28
  19. 2021In the light of feature distributions: moment matching for Neural Style Transfercited by 26
  20. 2022Generating natural images with direct Patch Distributions Matchingcited by 26
  21. 2023APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot Remote Sensing Image Generalization using CLIPcited by 24
  22. 2024FreeTuner: Any Subject in Any Style with Training-free Diffusioncited by 24
  23. 2021Robust Representation Learning via Perceptual Similarity Metricscited by 23
  24. 2022Neural Neighbor Style Transfercited by 23
  25. 2023Texture Learning Domain Randomization for Domain Generalized Segmentationcited by 23
  26. 2022Generalized One-shot Domain Adaptation of Generative Adversarial Networkscited by 19
  27. 2022StyleFool: Fooling Video Classification Systems via Style Transfercited by 18
  28. 2021Limitations of Post-Hoc Feature Alignment for Robustnesscited by 14
  29. 2022S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attentioncited by 14
  30. 2023Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylizationcited by 14
  31. 2024CoARF: Controllable 3D Artistic Style Transfer for Radiance Fieldscited by 14
  32. 2023Painterly Image Harmonization using Diffusion Modelcited by 12
  33. 2021DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfercited by 11
  34. 2022PCA-Based Knowledge Distillation Towards Lightweight and Content-Style Balanced Photorealistic Style Transfer Modelscited by 11
  35. 2022Mimetic Models: Ethical Implications of AI that Acts Like Youcited by 11
  36. 2022Painterly Image Harmonization in Dual Domainscited by 11
  37. 2022A diverse large-scale building dataset and a novel plug-and-play domain generalization method for building extractioncited by 10
  38. 2022Industrial Style Transfer with Large-scale Geometric Warping and Content Preservationcited by 9

50 most cited of 152 All 152 (JSON)