Research map / Image generation / Editing and style transfer
StyleFormer: Real-Time Arbitrary Style Transfer via Parametric Style Composition
Xiaolei Wu, Zhihao Hu, Lu Sheng, Dong Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add style bank generation and parametric content modulation to the transformer-only composition baseline (ablation) | StyleFormer · Qualitative comparison | content structure and style patterns | Improved |
| add content-conditioned affine coefficients (slicing operation) (ablation) | StyleFormer · Qualitative comparison | style richness and content consistency | Improved |
| add guide map (ablation) | StyleFormer · Qualitative comparison | style richness and content consistency | Improved |
| keep bias b in affine transform (versus removing it) (ablation) | StyleFormer · Qualitative comparison | holistic style background | Improved |
| use learned matrix A instead of identity matrix (ablation) | StyleFormer · Qualitative comparison | detailed strokes | Improved |
| increase weight alpha of A (ablation) | StyleFormer · Qualitative comparison | stroke strength | Improved |
Later papers that compared with this method
4 later accepted papers report StyleFormer as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Semantix: An Energy-guided Sampler for Semantic Style Transfer (ICLR 2025 · better on 1 of 1 shared result)
- Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network (CVPR 2024 · better on 2 of 4 shared results)
- General Image-to-Image Translation with One-Shot Image Guidance (ICCV 2023 · better on 2 of 2 shared results)
- Inversion-Based Style Transfer With Diffusion Models (CVPR 2023 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.89)
- HSI: A Holistic Style Injector for Arbitrary Style Transfer (CVPR 2025 · similarity 0.88)
- CSGO: Content-Style Composition in Text-to-Image Generation (NeurIPS 2025 · similarity 0.87)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.87)
- ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation (CVPR 2024 · similarity 0.87)
- SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
