mlsanityData to 7 Oct 2026

Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer

arXiv 2104.05376 ↗First posted 12 Apr 2021cs.CV eess.IVcited by 41

Not on the map. Why?

Abstract (arXiv)

Artistic style transfer aims at migrating the style from an example image to a content image. Currently, optimization-based methods have achieved great stylization quality, but expensive time cost restricts their practical applications. Meanwhile, feed-forward methods still fail to synthesize complex style, especially when holistic global and local patterns exist. Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle). LapStyle first transfers global style patterns in low-resolution via a Drafting Network. It then revises the local details in high-resolution via a Revision Network, which hallucinates a residual image according to the draft and the image textures extracted by Laplacian filtering. Higher resolution details can be easily generated by stacking Revision Networks with multiple Laplacian pyramid levels. The final stylized image is obtained by aggregating outputs of all pyramid levels. %We also introduce a patch discriminator to better learn local patterns adversarially. Experiments demonstrate that our method can synthesize high quality stylized images in real time, where holistic style patterns are properly transferred.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 31 of its 39 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

31 of 39 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  5. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  6. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  7. 2017Universal Style Transfer via Feature Transformscited by 352
  8. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  9. 2016A Learned Representation For Artistic Stylecited by 340
  10. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  11. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  12. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 197
19 more
  1. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  2. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 173
  3. 2019Style Transfer by Relaxed Optimal Transport and Self-Similaritycited by 167
  4. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  5. 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
  6. 2017Visual Attribute Transfer through Deep Image Analogycited by 123
  7. 2018Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decorationcited by 115
  8. 2016Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesiscited by 102
  9. 2016Controlling Perceptual Factors in Neural Style Transfercited by 99
  10. 2017Coherent Online Video Style Transfercited by 96
  11. 2016Fast Patch-based Style Transfer of Arbitrary Stylecited by 92
  12. 2017StyleBank: An Explicit Representation for Neural Image Style Transfercited by 89
  13. 2018Arbitrary Style Transfer with Deep Feature Reshufflecited by 75
  14. 2017Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Lossescited by 69
  15. 2017Multi-style Generative Network for Real-time Transfercited by 61
  16. 2017Diversified Texture Synthesis with Feed-forward Networkscited by 59
  17. 2016Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfercited by 30
  18. 2016Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworkscited by 22
  19. 2018Stereoscopic Neural Style Transfercited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 11; 2023: 19; 2024: 4; 2025: 2; 2026: 1.

41 papers.

Sort:

By area:

  1. 2021StyTr2: Image Style Transfer with Transformerscited by 186
  2. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Modelscited by 154
  3. 2021Paint Transformer: Feed Forward Neural Painting with Stroke Predictioncited by 61
  4. 2021High-Resolution Image Harmonization via Collaborative Dual Transformationscited by 55
  5. 2022CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfercited by 46
  6. 2022DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylizationcited by 45
  7. 2022AesUST: Towards Aesthetic-Enhanced Universal Style Transfercited by 21
  8. 2024One-Shot Diffusion Mimicker for Handwritten Text Generationcited by 20
  9. 2022MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfercited by 19
  10. 2023Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaboratecited by 17
  11. 2023InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Advisercited by 17
  12. 2022S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attentioncited by 14
29 more
  1. 2022Single UHD Image Dehazing via Interpretable Pyramid Networkcited by 13
  2. 2021Texture Reformer: Towards Fast and Universal Interactive Texture Transfercited by 12
  3. 2023Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transferscited by 12
  4. 2023StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Modelcited by 10
  5. 2022Industrial Style Transfer with Large-scale Geometric Warping and Content Preservationcited by 9
  6. 2023NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistencycited by 7
  7. 2022Image Harmonization by Matching Regional Referencescited by 6
  8. 2023ArtFusion: Controllable Arbitrary Style Transfer using Dual Conditional Latent Diffusion Modelscited by 4
  9. 2023InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfercited by 4
  10. 2023SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspectivecited by 3
  11. 2023AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfercited by 3
  12. 2022Laplacian Pyramid-like Autoencodercited by 2
  13. 2023A Laplacian Pyramid Based Generative H&E Stain Augmentation Networkcited by 2
  14. 2023TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfercited by 2
  15. 2024SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Style Transfercited by 2
  16. 2022Interactive Style Transfer: All is Your Palettecited by 1
  17. 2023Controlling Neural Style Transfer with Deep Reinforcement Learningcited by 1
  18. 2025RLMiniStyler: Light-weight RL Style Agent for Arbitrary Sequential Neural Style Generationcited by 1
  19. 2022Arbitrary Style Transfer with Structure Enhancement by Combining the Global and Local Losscited by 0
  20. 2023Edge Enhanced Image Style Transfer via Transformerscited by 0
  21. 2023Few-shot Face Image Translation via GAN Prior Distillationcited by 0
  22. 2023Texturize a GAN Using a Single Imagecited by 0
  23. 2023RL-I2IT: Image-to-Image Translation with Deep Reinforcement Learningcited by 0
  24. 2023An easy zero-shot learning combination: Texture Sensitive Semantic Segmentation IceHrNet and Advanced Style Transfer Learning Strategycited by 0
  25. 2023Painterly Image Harmonization via Adversarial Residual Learningcited by 0
  26. 2024DLP-GAN: learning to draw modern Chinese landscape photos with generative adversarial networkcited by 0
  27. 2024RoNet: Rotation-oriented Continuous Image Translationcited by 0
  28. 2025Coarse-to-Fine Structure-Aware Artistic Style Transfercited by 0
  29. 2026LEMMA: Laplacian pyramids for Efficient Marine SeMAntic Segmentationcited by 0