# MDiff4STR: Mask Diffusion Model for Scene Text Recognition arXiv: https://arxiv.org/abs/2512.01422 ยท HTML: https://mlsanity.com/paper/2512.01422/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. - Builds on 32 of its 52 references that are in the map. - First posted on arXiv 1 Dec 2025. ## Placed in - Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/) ## Builds on (most cited first, 30 of 32) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016) - [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014) - [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024) - [Simplified and Generalized Masked Diffusion for Discrete Data](https://mlsanity.com/paper/2406.04329/) (2024) - [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016) - [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014) - [Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition](https://mlsanity.com/paper/2103.06495/) (2021) - [LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning](https://mlsanity.com/paper/2505.16933/) (2025) - [Towards Accurate Scene Text Recognition with Semantic Reasoning Networks](https://mlsanity.com/paper/2003.12294/) (2020) - [Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition](https://mlsanity.com/paper/1811.00751/) (2018) - [Robust Scene Text Recognition with Automatic Rectification](https://mlsanity.com/paper/1603.03915/) (2016) - [SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition](https://mlsanity.com/paper/2005.10977/) (2020) - [PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System](https://mlsanity.com/paper/2206.03001/) (2022) - [Decoupled Attention Network for Text Recognition](https://mlsanity.com/paper/1912.10205/) (2019) - [From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network](https://mlsanity.com/paper/2108.09661/) (2021) - [SVTR: Scene Text Recognition with a Single Visual Model](https://mlsanity.com/paper/2205.00159/) (2022) - [RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition](https://mlsanity.com/paper/2007.07542/) (2020) - [NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition](https://mlsanity.com/paper/1806.00926/) (2018) - [MASTER: Multi-Aspect Non-local Network for Scene Text Recognition](https://mlsanity.com/paper/1910.02562/) (2019) - [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021) - [Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer](https://mlsanity.com/paper/2311.13120/) (2023) - [Revisiting Scene Text Recognition: A Data Perspective](https://mlsanity.com/paper/2307.08723/) (2023) - [CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition](https://mlsanity.com/paper/2111.11011/) (2021) - [Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning](https://mlsanity.com/paper/2309.01083/) (2023) - [Self-supervised Implicit Glyph Attention for Text Recognition](https://mlsanity.com/paper/2203.03382/) (2022) - [Out of Length Text Recognition with Sub-String Matching](https://mlsanity.com/paper/2407.12317/) (2024) - [Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach](https://mlsanity.com/paper/2308.08806/) (2023) ## Built on by (most cited first, 4 of 4) - [ICPR 2026 Competition on Low-Resolution License Plate Recognition](https://mlsanity.com/paper/2604.22506/) (2026) - [Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods](https://mlsanity.com/paper/2606.24484/) (2026) - [All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts](https://mlsanity.com/paper/2609.24058/) (2026) - [Frequency Decoupled Framework for Screen Content Image Super-Resolution](https://mlsanity.com/paper/2606.09029/) (2026) ## Abstract (arXiv) Mask Diffusion Models (MDMs) have recently emerged as a promising alternative to auto-regressive models (ARMs) for vision-language tasks, owing to their flexible balance of efficiency and accuracy. In this paper, for the first time, we introduce MDMs into the Scene Text Recognition (STR) task. We show that vanilla MDM lags behind ARMs in terms of accuracy, although it improves recognition efficiency. To bridge this gap, we propose MDiff4STR, a Mask Diffusion model enhanced with two key improvement strategies tailored for STR. Specifically, we identify two key challenges in applying MDMs to STR: noising gap between training and inference, and overconfident predictions during inference. Both significantly hinder the performance of MDMs. To mitigate the first issue, we develop six noising strategies that better align training with inference behavior. For the second, we propose a token-replacement noise mechanism that provides a non-mask noise type, encouraging the model to reconsider and revise overly confident but incorrect predictions. We conduct extensive evaluations of MDiff4STR on both standard and challenging STR benchmarks, covering diverse scenarios including irregular, artistic, occluded, and Chinese text, as well as whether the use of pretraining. Across these settings, MDiff4STR consistently outperforms popular STR models, surpassing state-of-the-art ARMs in accuracy, while maintaining fast inference with only three denoising steps. Code: https://github.com/Topdu/OpenOCR.