mlsanityData to 14 Oct 2026

StyTr2: Image Style Transfer with Transformers

arXiv 2105.14576 ↗First posted 30 May 2021cs.CV eess.IVcited by 187

Not on the map. Why?

Cited by 51 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content. Owing to the locality in convolutional neural networks (CNNs), extracting and maintaining the global information of input images is difficult. Therefore, traditional neural style transfer methods face biased content representation. To address this critical issue, we take long-range dependencies of input images into account for image style transfer by proposing a transformer-based approach called StyTr2. In contrast with visual transformers for other vision tasks, StyTr2 contains two different transformer encoders to generate domain-specific sequences for content and style, respectively. Following the encoders, a multi-layer transformer decoder is adopted to stylize the content sequence according to the style sequence. We also analyze the deficiency of existing positional encoding methods and propose the content-aware positional encoding (CAPE), which is scale-invariant and more suitable for image style transfer tasks. Qualitative and quantitative experiments demonstrate the effectiveness of the proposed StyTr2 compared with state-of-the-art CNN-based and flow-based approaches. Code and models are available at https://github.com/diyiiyiii/StyTR-2.

Key facts. Cited by 187 papers in the map (data through 14 Oct 2026). Builds on 51 of its 66 references that are in the map. First posted on arXiv 30 May 2021.

Builds on

51 of 66 references.

References · 51

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  7. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  8. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  9. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  10. 2020End-to-End Object Detection with Transformerscited by 7,414
  11. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
38 more
  1. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  2. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  3. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  5. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  6. 2018Self-Attention with Relative Position Representationscited by 1,120
  7. 2020On Layer Normalization in the Transformer Architecturecited by 922
  8. 2020Pre-Trained Image Processing Transformercited by 893
  9. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  10. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 639
  11. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  12. 2017Universal Style Transfer via Feature Transformscited by 354
  13. 2016A Learned Representation For Artistic Stylecited by 341
  14. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  15. 2021Vision Transformers are Robust Learnerscited by 207
  16. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 198
  17. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  18. 2020How Much Position Information Do Convolutional Neural Networks Encode?cited by 172
  19. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  20. 2017Demystifying Neural Style Transfercited by 152
  21. 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
  22. 2018Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decorationcited by 115
  23. 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
  24. 2017StyleBank: An Explicit Representation for Neural Image Style Transfercited by 89
  25. 2019Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representationcited by 84
  26. 2020Arbitrary Video Style Transfer via Multi-Channel Correlationcited by 84
  27. 2020Arbitrary Style Transfer via Multi-Adaptation Networkcited by 70
  28. 2017Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Lossescited by 69
  29. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  30. 2020Collaborative Distillation for Ultra-Resolution Universal Style Transfercited by 52
  31. 2019Attention-aware Multi-stroke Style Transfercited by 47
  32. 2019A Closed-form Solution to Universal Style Transfercited by 42
  33. 2019Diversified Arbitrary Style Transfer via Deep Feature Perturbationcited by 42
  34. 2021Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfercited by 41
  35. 2019Ultrafast Photorealistic Style Transfer via Neural Architecture Searchcited by 39
  36. 2019Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfercited by 36
  37. 2018EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfercited by 13
  38. 2020Distribution Aligned Multimodal and Multi-Domain Image Stylizationcited by 10

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 14; 2023: 50; 2024: 44; 2025: 51; 2026: 28.

187 papers.

Sort:

By area:

  1. 2022Inversion-Based Style Transfer with Diffusion Modelscited by 291
  2. 2023StyleDrop: Text-to-Image Generation in Any Stylecited by 199
  3. 2023Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfercited by 196
  4. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Modelscited by 155
  5. 2024Implicit Style-Content Separation using B-LoRAcited by 135
  6. 2022Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learningcited by 93
  7. 2024CSGO: Content-Style Composition in Text-to-Image Generationcited by 78
  8. 2024DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representationscited by 68
  9. 2024StyleShot: A Snapshot on Any Stylecited by 62
  10. 2024UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Modelscited by 50
  11. 2022ArtFID: Quantitative Evaluation of Neural Style Transfercited by 49
  12. 2023Photoswap: Personalized Subject Swapping in Imagescited by 47
38 more
  1. 2022DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylizationcited by 45
  2. 2023ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priorscited by 40
  3. 2023ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptationcited by 40
  4. 2023StyleAdapter: A Unified Stylized Image Generation Modelcited by 39
  5. 2023Neural Preset for Color Style Transfercited by 36
  6. 2023AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networkscited by 34
  7. 2025Attention Distillation: A Unified Approach to Visual Characteristics Transfercited by 33
  8. 2024StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Modelscited by 32
  9. 2023General Image-to-Image Translation with One-Shot Image Guidancecited by 31
  10. 2022Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusioncited by 30
  11. 2023DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Modelscited by 27
  12. 2024FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Modelscited by 22
  13. 2022MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfercited by 19
  14. 2022QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelitycited by 18
  15. 2023SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolutioncited by 18
  16. 2024MoST: Motion Style Transformer between Diverse Action Contentscited by 18
  17. 2023Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaboratecited by 17
  18. 2023InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Advisercited by 17
  19. 2023Z^*: Zero-shot Style Transfer via Attention Rearrangementcited by 17
  20. 2022All-to-key Attention for Arbitrary Style Transfercited by 16
  21. 2023DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Datacited by 15
  22. 2022S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attentioncited by 14
  23. 2023Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfercited by 14
  24. 2024SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editingcited by 13
  25. 2023Learning Dynamic Style Kernels for Artistic Style Transfercited by 12
  26. 2023Painterly Image Harmonization using Diffusion Modelcited by 12
  27. 2022Painterly Image Harmonization in Dual Domainscited by 11
  28. 2023StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Modelcited by 10
  29. 2023A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learningcited by 10
  30. 2023Learning to Evaluate the Artness of AI-generated Imagescited by 10
  31. 2024Anything in Any Scene: Photorealistic Video Object Insertioncited by 9
  32. 2024Applications of Generative AI (GAI) for Mobile and Wireless Networking: A Surveycited by 9
  33. 2025AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Modelscited by 9
  34. 2025Video Color Grading via Look-Up Table Generationcited by 9
  35. 2023Learning Disentangled Prompts for Compositional Image Synthesiscited by 8
  36. 2025Free-Lunch Color-Texture Disentanglement for Stylized Image Generationcited by 8
  37. 2025CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splattingcited by 8
  38. 2024Backdoor Attacks against Image-to-Image Networkscited by 7

50 most cited of 187 All 187 (JSON)