Research map / Image generation / Editing and style transfer
StyleFM: Frequency Manipulation Empowered by Recursive Attention on Diffusion Models for Arbitrary Style Transfer
Yingnan Ma, Zhenye Liu, Siying Liu, Anup Basu
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 tripartite frequency manipulation (FM) to the baseline (ablation) | StyleFM baseline · StyleID test set | LPIPSs / LPIPSc: LPIPSs 0.72 -> 0.6891; LPIPSc 0.5091 -> 0.5192 | Mixed |
| add recursive attention (RA) to the baseline (ablation) | StyleFM baseline · StyleID test set | LPIPSs / LPIPSc: LPIPSs 0.72 -> 0.7256; LPIPSc 0.5091 -> 0.4517 | Mixed |
| combine FM and RA (ablation) | StyleFM · StyleID test set | LPIPSs / LPIPSc: LPIPSs 0.72 -> 0.6928; LPIPSc 0.5091 -> 0.4955 | Improved |
| increase content superposition parameter alpha from 0 to 0.5 (ablation) | StyleFM · StyleID test set | LPIPSc: 0.4717 -> 0.4689 | Improved |
| increase content superposition parameter alpha from 0 to 0.5 (ablation) | StyleFM · StyleID test set | LPIPSs: 0.7038 -> 0.7042 | No clear effect |
| raise mid-high frequency boundary (ablation) | StyleFM · StyleID test set | LPIPSc / LPIPSs | Mixed |
| use StyleFM versus StyleID baseline | StyleFM · StyleID test set | LPIPSArt: 2.571 -> 2.532 | Improved |
| use recursion parameter lambda to propagate attention across timesteps (ablation) | StyleFM · qualitative | content and color embedding | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- StyTr2 — StyTr2: Image Style Transfer With Transformers (CVPR 2022) · better on 1 of 1 shared result
- ArtFlow — ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows (CVPR 2021) · 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
- Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer (CVPR 2024 · similarity 0.92)
- StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer (CVPR 2025 · similarity 0.90)
- Z*: Zero-shot Style Transfer via Attention Reweighting (CVPR 2024 · similarity 0.90)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.89)
- Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models (ICLR 2025 · similarity 0.88)
- Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image Generation (CVPR 2025 · similarity 0.88)
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.
