mlsanityData to 7 Oct 2026

Color and Texture Dual Pipeline Lightweight Style Transfer

arXiv 2310.01321 ↗First posted 2 Oct 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Style transfer methods typically generate a single stylized output of color and texture coupling for reference styles, and color transfer schemes may introduce distortion or artifacts when processing reference images with duplicate textures. To solve the problem, we propose a Color and Texture Dual Pipeline Lightweight Style Transfer CTDP method, which employs a dual pipeline method to simultaneously output the results of color and texture transfer. Furthermore, we designed a masked total variation loss to suppress artifacts and small texture representations in color transfer results without affecting the semantic part of the content. More importantly, we are able to add texture structures with controllable intensity to color transfer results for the first time. Finally, we conducted feature visualization analysis on the texture generation mechanism of the framework and found that smoothing the input image can almost completely eliminate this texture structure. In comparative experiments, the color and texture transfer results generated by CTDP both achieve state-of-the-art performance. Additionally, the weight of the color transfer branch model size is as low as 20k, which is 100-1500 times smaller than that of other state-of-the-art models.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 41 references that are in the map. First posted on arXiv 2 Oct 2023.

Builds on

33 of 41 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  6. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  7. 2017Universal Style Transfer via Feature Transformscited by 352
  8. 2016A Learned Representation For Artistic Stylecited by 340
  9. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  10. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 197
  11. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  12. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 173
21 more
  1. 2017Deep Photo Style Transfercited by 168
  2. 2019Style Transfer by Relaxed Optimal Transport and Self-Similaritycited by 167
  3. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  4. 2017Demystifying Neural Style Transfercited by 152
  5. 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
  6. 2016Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesiscited by 102
  7. 2017StyleBank: An Explicit Representation for Neural Image Style Transfercited by 89
  8. 2019Dynamic Instance Normalization for Arbitrary Style Transfercited by 83
  9. 2018Arbitrary Style Transfer with Deep Feature Reshufflecited by 75
  10. 2017Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Lossescited by 69
  11. 2017Multi-style Generative Network for Real-time Transfercited by 61
  12. 2017Diversified Texture Synthesis with Feed-forward Networkscited by 59
  13. 2020Collaborative Distillation for Ultra-Resolution Universal Style Transfercited by 52
  14. 2018Stroke Controllable Fast Style Transfer with Adaptive Receptive Fieldscited by 33
  15. 2016Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfercited by 30
  16. 2021PhotoWCT2: Compact Autoencoder for Photorealistic Style Transfer Resulting from Blockwise Training and Skip Connections of High-Frequency Residualscited by 30
  17. 2023CAP-VSTNet: Content Affinity Preserved Versatile Style Transfercited by 24
  18. 2016Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworkscited by 22
  19. 2022MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfercited by 19
  20. 2018MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfercited by 16
  21. 2021DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfercited by 11

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.