# ArtChart: Faithful Artistic Chart Generation with Integrated Text Rendering

arXiv: https://arxiv.org/abs/2607.16060 · HTML: https://mlsanity.com/paper/2607.16060/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Builds on (most cited first, 15 of 15)

- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [AnyText: Multilingual Visual Text Generation And Editing](https://mlsanity.com/paper/2311.03054/) (2023)
- [ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback](https://mlsanity.com/paper/2404.07987/) (2024)
- [TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering](https://mlsanity.com/paper/2311.16465/) (2023)
- [Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering](https://mlsanity.com/paper/2403.09622/) (2024)
- [Flow-OPD: On-Policy Distillation for Flow Matching Models](https://mlsanity.com/paper/2605.08063/) (2026)
- [EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering](https://mlsanity.com/paper/2505.24417/) (2025)
- [Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model](https://mlsanity.com/paper/2304.14630/) (2023)
- [IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation](https://mlsanity.com/paper/2601.04498/) (2026)
- [TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering](https://mlsanity.com/paper/2602.20903/) (2026)
- [TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards](https://mlsanity.com/paper/2605.19320/) (2026)
- [ChartEditor: A Human-AI Paired Tool for Authoring Pictorial Charts](https://mlsanity.com/paper/2501.07320/) (2025)
- [ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control](https://mlsanity.com/paper/2603.14209/) (2026)
- [POCA: Pareto-Optimal Curriculum Alignment for Visual Text Generation](https://mlsanity.com/paper/2604.24171/) (2026)

## Abstract (arXiv)

Artistic charts combine data visualization with expressive marks, textures, and typography, but they are difficult for image generators: an output is useful only when its stylization preserves chart geometry, exact in-image text, and the semantic binding between labels and marks. We introduce ArtChart, a framework for faithful artistic chart generation with integrated text rendering. Given a structured chart specification and an artistic prompt, ArtChart first renders a text-free grayscale layout that encodes the target chart geometry, then trains a chart-specific control module to preserve mathematical structure. To address the remaining text and layout errors, we further refine the generation policy through GRPO-based reinforcement learning with OCR-based text rewards, VLM-based layout rewards, and aesthetic rewards. A multi-expert distillation stage reconciles these objectives by distilling single-reward experts into one balanced generation policy. We also construct ArtChart-Bench, a bilingual 2K-prompt benchmark covering four chart types, controlled value distributions, diverse label/value formats, and 15 artistic styles, together with ArtChart-Eval, a six-axis evaluation protocol measuring mathematical logic, text accuracy, text layout, aesthetics, instruction following, and readability. Experiments on ArtChart-Bench show that ArtChart consistently outperforms prompt-only, image-editing, and generic ControlNet baselines, with the largest gains on mathematical fidelity and label-layout binding while maintaining competitive visual quality. These results suggest that artistic chart generation should be evaluated as reliable visual communication rather than as generic stylized image synthesis.