Research map / Image generation / Editing and style transfer
Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset
Yuhai Deng, Huimin She, Wei Shen, Meng Li, Ruoxi Wu, Lunxi Yuan, Xiang Li
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 |
|---|---|---|---|
| train existing methods on TST100K triplets | CAP-VSTNet · TST2K | dE: 11.87 -> 7.359 | Improved |
| train Neural Preset on TST100K | Neural Preset · TST2K | dE: 10.51 -> 7.886 | Improved |
| retrained models on PST50 zero-shot | Neural Preset · PST50 | dE: 19.53 -> 17.81 | Improved |
| add tone-scorer and aesthetic filtering to TST100K (ablation) | ICTone · TST2K | dE: 9.859 -> 6.035 | Improved |
| add tone reward feedback with contrastive scorer (ablation) | ICTone · TST2K | dE: 6.035 -> 5.795 | Improved |
| add preference learning to reward scorer (ablation) | ICTone · TST2K | CD: 2.765 -> 2.634 | Improved |
| add preference learning to tone scorer (ablation) | tone style scorer · IFFI retrieval | Recall@1: 93.19 -> 97.50 | Improved |
| tone-specific scorer vs general style descriptor CSD | tone scorer · IFFI retrieval | Recall@1: 63.13 -> 93.19 | Improved |
| ICTone vs best baseline on PST50 dE | ICTone · PST50 | dE: 11.25 -> 12.81 | Hurt |
| ICTone vs Nano Banana2 on aesthetics | ICTone · TST2K | Aes: 0.7885 -> 0.7904 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SA-LUT — SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer (ICCV 2025) · better on 3 of 4 shared results
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
- Automatic Content-Aware Color and Tone Stylization (CVPR 2016 · similarity 0.89)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.88)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.88)
- Enlightening Photographic Style Transfer with a Self-Supervised Photographic Embedding (ECCV 2026 · similarity 0.88)
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (AAAI 2024 · similarity 0.87)
- CSGO: Content-Style Composition in Text-to-Image Generation (NeurIPS 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.
