# DreamText: High Fidelity Scene Text Synthesis

arXiv: https://arxiv.org/abs/2405.14701 · HTML: https://mlsanity.com/paper/2405.14701/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 24 of 24)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Break-A-Scene: Extracting Multiple Concepts from a Single Image](https://mlsanity.com/paper/2305.16311/) (2023)
- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [AnyText: Multilingual Visual Text Generation And Editing](https://mlsanity.com/paper/2311.03054/) (2023)
- [Scene Text Recognition with Permuted Autoregressive Sequence Models](https://mlsanity.com/paper/2207.06966/) (2022)
- [Editing Text in the Wild](https://mlsanity.com/paper/1908.03047/) (2019)
- [Vision Transformer for Fast and Efficient Scene Text Recognition](https://mlsanity.com/paper/2105.08582/) (2021)
- [Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering](https://mlsanity.com/paper/2403.09622/) (2024)
- [UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models](https://mlsanity.com/paper/2312.04884/) (2023)
- [SwapText: Image Based Texts Transfer in Scenes](https://mlsanity.com/paper/2003.08152/) (2020)
- [STEFANN: Scene Text Editor using Font Adaptive Neural Network](https://mlsanity.com/paper/1903.01192/) (2019)
- [Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts](https://mlsanity.com/paper/2104.00887/) (2021)
- [Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach](https://mlsanity.com/paper/2011.14021/) (2020)
- [Improving Diffusion Models for Scene Text Editing with Dual Encoders](https://mlsanity.com/paper/2304.05568/) (2023)
- [DiffUTE: Universal Text Editing Diffusion Model](https://mlsanity.com/paper/2305.10825/) (2023)
- [Exploring Stroke-Level Modifications for Scene Text Editing](https://mlsanity.com/paper/2212.01982/) (2022)
- [Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator](https://mlsanity.com/paper/2205.00146/) (2022)
- [De-rendering Stylized Texts](https://mlsanity.com/paper/2110.01890/) (2021)
- [High-fidelity Person-centric Subject-to-Image Synthesis](https://mlsanity.com/paper/2311.10329/) (2023)
- [PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering](https://mlsanity.com/paper/2403.05053/) (2024)
- [Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation](https://mlsanity.com/paper/2403.16422/) (2024)
- [Enhancing Object Coherence in Layout-to-Image Synthesis](https://mlsanity.com/paper/2311.10522/) (2023)

## Built on by (most cited first, 18 of 18)

- [UniREditBench: A Unified Reasoning-based Image Editing Benchmark](https://mlsanity.com/paper/2511.01295/) (2025)
- [Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation](https://mlsanity.com/paper/2605.28091/) (2026)
- [TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering](https://mlsanity.com/paper/2602.20903/) (2026)
- [ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing](https://mlsanity.com/paper/2601.03467/) (2026)
- [OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities](https://mlsanity.com/paper/2507.15085/) (2025)
- [TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition](https://mlsanity.com/paper/2412.01137/) (2024)
- [MagicFace: Training-free Universal-Style Human Image Customized Synthesis](https://mlsanity.com/paper/2408.07433/) (2024)
- [TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards](https://mlsanity.com/paper/2605.19320/) (2026)
- [DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy](https://mlsanity.com/paper/2512.01302/) (2025)
- [InnoText: A Unified Model for Visual Text Generation and Editing](https://mlsanity.com/paper/2607.22101/) (2026)
- [TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters](https://mlsanity.com/paper/2608.19637/) (2026)
- [SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Design](https://mlsanity.com/paper/2511.13285/) (2025)
- [Towards Training-Free Scene Text Editing](https://mlsanity.com/paper/2603.24571/) (2026)
- [Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning](https://mlsanity.com/paper/2605.15523/) (2026)
- [TextDiffuser-RL: Efficient and Robust Text Layout Optimization for High-Fidelity Text-to-Image Synthesis](https://mlsanity.com/paper/2505.19291/) (2025)
- [Edit Fidelity Field: Semantics-Aware Region Isolation for Training-Free Scene Text Editing](https://mlsanity.com/paper/2604.17500/) (2026)
- [Planning and Rendering in Concert: DeepFusion of Autoregressive Layouts and Diffusion for Visual Text Generation](https://mlsanity.com/paper/2609.22916/) (2026)
- [Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation](https://mlsanity.com/paper/2610.18284/) (2026)

## Abstract (arXiv)

Scene text synthesis involves rendering specified texts onto arbitrary images. Current methods typically formulate this task in an end-to-end manner but lack effective character-level guidance during training. Besides, their text encoders, pre-trained on a single font type, struggle to adapt to the diverse font styles encountered in practical applications. Consequently, these methods suffer from character distortion, repetition, and absence, particularly in polystylistic scenarios. To this end, this paper proposes DreamText for high-fidelity scene text synthesis. Our key idea is to reconstruct the diffusion training process, introducing more refined guidance tailored to this task, to expose and rectify the model's attention at the character level and strengthen its learning of text regions. This transformation poses a hybrid optimization challenge, involving both discrete and continuous variables. To effectively tackle this challenge, we employ a heuristic alternate optimization strategy. Meanwhile, we jointly train the text encoder and generator to comprehensively learn and utilize the diverse font present in the training dataset. This joint training is seamlessly integrated into the alternate optimization process, fostering a synergistic relationship between learning character embedding and re-estimating character attention. Specifically, in each step, we first encode potential character-generated position information from cross-attention maps into latent character masks. These masks are then utilized to update the representation of specific characters in the current step, which, in turn, enables the generator to correct the character's attention in the subsequent steps. Both qualitative and quantitative results demonstrate the superiority of our method to the state of the art.