mlsanityData to 14 Oct 2026

CDST: Color Disentangled Style Transfer for Universal Style Reference Customization

arXiv 2506.13770 ↗First posted 22 May 2025cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce Color Disentangled Style Transfer (CDST), a novel and efficient two-stream style transfer training paradigm which completely isolates color from style and forces the style stream to be color-blinded. With one same model, CDST unlocks universal style transfer capabilities in a tuning-free manner during inference. Especially, the characteristics-preserved style transfer with style and content references is solved in the tuning-free way for the first time. CDST significantly improves the style similarity by multi-feature image embeddings compression and preserves strong editing capability via our new CDST style definition inspired by Diffusion UNet disentanglement law. By conducting thorough qualitative and quantitative experiments and human evaluations, we demonstrate that CDST achieves state-of-the-art results on various style transfer tasks.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

32 of 45 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2022Scalable Diffusion Models with Transformerscited by 6,054
  10. 2022Classifier-Free Diffusion Guidancecited by 5,847
  11. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  12. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
20 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  2. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  3. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  4. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  5. 2023P+: Extended Textual Conditioning in Text-to-Image Generationcited by 242
  6. 2023StyleDrop: Text-to-Image Generation in Any Stylecited by 199
  7. 2024InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generationcited by 170
  8. 2024Measuring Style Similarity in Diffusion Modelscited by 109
  9. 2024CSGO: Content-Style Composition in Text-to-Image Generationcited by 78
  10. 2024Instruct-Imagen: Image Generation with Multi-modal Instructioncited by 65
  11. 2023StyleAdapter: A Unified Stylized Image Generation Modelcited by 39
  12. 2020V4D:4D Convolutional Neural Networks for Video-level Representation Learningcited by 33
  13. 2024ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglementcited by 28
  14. 2023Forgedit: Text Guided Image Editing via Learning and Forgettingcited by 26
  15. 2016Preserving Color in Neural Artistic Style Transfercited by 20
  16. 2022TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoningcited by 12
  17. 2020Knowledge Integration Networks for Action Recognitioncited by 8
  18. 2025Free-Lunch Color-Texture Disentanglement for Stylized Image Generationcited by 8
  19. 2025Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Modelscited by 7
  20. 2024Hyper-parameter tuning for text guided image editingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026TeleStyle: Content-Preserving Style Transfer in Images and Videoscited by 5
  2. 2026QwenStyle: Content-Preserving Style Transfer with Qwen-Image-Editcited by 4
  3. 2026Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learningcited by 1
  4. 2026The Latent Color Subspace: Emergent Order in High-Dimensional Chaoscited by 0
  5. 2026UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglementcited by 0
  6. 2026TeleStyle V2: Beyond Content-Preserving Style Transfer with Self-Distillation and Distribution-Matching-Distillationcited by 0