Research map / Image generation / Editing and style transfer
CHARTSTYLE-100K: A Large-Scale Dataset for Structured Visualization Style Transfer
Yuwei Yang, Tianchi Xie, Jinhong Ni, Yukai Guo, Jing Zhang, Liang Zheng, Yalong Bai, YUHUI YUAN
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 general-domain style transfer fine-tuning (stage 1) (ablation) | Qwen-Image-Edit · ChartStyle-Bench | Content leakage: 0.51 -> 0.13 | Improved |
| add general-domain style transfer fine-tuning (stage 1) (ablation) | Qwen-Image-Edit · ChartStyle-Bench | Overall: 1.58 -> 2.45 | Improved |
| add chart-only fine-tuning (stage 2) without stage 1 (ablation) | Qwen-Image-Edit · ChartStyle-Bench | Content consistency: 2.75 -> 2.45 | Hurt |
| add chart-only fine-tuning (stage 2) (ablation) | Qwen-Image-Edit · ChartStyle-Bench | Content leakage: 0.51 -> 0.03 | Improved |
| add stage 1 before stage 2 (progressive training) (ablation) | Qwen-Image-Edit · ChartStyle-Bench | Overall: 2.53 -> 3.03 | Improved |
| add stage 1 before stage 2 (progressive training) (ablation) | Qwen-Image-Edit · ChartStyle-Bench | OCRScore: 0.54 -> 0.76 | Improved |
| add style-space resampling (ablation) | ReChart · ChartStyle-Bench | Overall: 2.71 -> 3.03 | Improved |
| add style-space resampling (ablation) | ReChart · ChartStyle-Bench | Style similarity: 2.75 -> 2.90 | Improved |
| add style-space resampling (ablation) | ReChart · ChartStyle-Bench | Content consistency: 3.57 -> 3.96 | Improved |
| larger text size | ReChart · ChartStyle-Bench (text size buckets) | OCR F1: 0.56 -> 0.78 | Improved |
| ReChart vs GPT-Image-1.5 | ReChart · ChartStyle-Bench | Overall: 2.82 -> 3.03 | Improved |
| pixel-based editing instead of code-based pipeline | ReChart · ChartStyle-Bench | Visual quality | 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.
- StyleStudio — StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements (CVPR 2025) · better on 1 of 1 shared result
- CSGO — CSGO: Content-Style Composition in Text-to-Image Generation (NeurIPS 2025) · 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
- ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing (ICML 2026 · similarity 0.89)
- CSGO: Content-Style Composition in Text-to-Image Generation (NeurIPS 2025 · similarity 0.88)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.87)
- CLeaR: A Unified Framework for Resolving the Leakage–Degradation Dilemma in Style Transfer (NeurIPS 2026 · similarity 0.86)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.85)
- ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding (CVPR 2026 · similarity 0.85)
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.
