# TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution arXiv: https://arxiv.org/abs/2308.06743 ยท HTML: https://mlsanity.com/paper/2308.06743/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. - Builds on 31 of its 49 references that are in the map. - First posted on arXiv 13 Aug 2023. ## Placed in - Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/) ## Builds on (most cited first, 30 of 31) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015) - [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017) - [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016) - [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021) - [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021) - [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018) - [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014) - [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021) - [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022) - [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015) - [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022) - [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021) - [Deblurring via Stochastic Refinement](https://mlsanity.com/paper/2112.02475/) (2021) - [Shape Robust Text Detection with Progressive Scale Expansion Network](https://mlsanity.com/paper/1903.12473/) (2019) - [Classification Accuracy Score for Conditional Generative Models](https://mlsanity.com/paper/1905.10887/) (2019) - [Scene Text Detection and Recognition: The Deep Learning Era](https://mlsanity.com/paper/1811.04256/) (2018) - [Scene Text Image Super-Resolution in the Wild](https://mlsanity.com/paper/2005.03341/) (2020) - [Text Prior Guided Scene Text Image Super-resolution](https://mlsanity.com/paper/2106.15368/) (2021) - [DocDiff: Document Enhancement via Residual Diffusion Models](https://mlsanity.com/paper/2305.03892/) (2023) - [CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition](https://mlsanity.com/paper/2111.11011/) (2021) - [A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution](https://mlsanity.com/paper/2203.09388/) (2022) - [Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination](https://mlsanity.com/paper/1911.03624/) (2019) - [A Multi-Object Rectified Attention Network for Scene Text Recognition](https://mlsanity.com/paper/1901.03003/) (2019) - [Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution](https://mlsanity.com/paper/2112.08171/) (2021) - [C3-STISR: Scene Text Image Super-resolution with Triple Clues](https://mlsanity.com/paper/2204.14044/) (2022) - [Levenshtein OCR](https://mlsanity.com/paper/2209.03594/) (2022) - [Improving Scene Text Image Super-resolution via Dual Prior Modulation Network](https://mlsanity.com/paper/2302.10414/) (2023) - [Deep Laplacian Pyramid Network for Text Images Super-Resolution](https://mlsanity.com/paper/1811.10449/) (2018) ## Built on by (most cited first, 10 of 10) - [XReal: Realistic Anatomy and Pathology-Aware X-ray Generation via Controllable Diffusion Model](https://mlsanity.com/paper/2403.09240/) (2024) - [Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2311.13317/) (2023) - [PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2311.17955/) (2023) - [Unified Diffusion Transformer for High-fidelity Text-Aware Image Restoration](https://mlsanity.com/paper/2512.08922/) (2025) - [TextDoctor: Unified Document Image Inpainting via Patch Pyramid Diffusion Models](https://mlsanity.com/paper/2503.04021/) (2025) - [SFA: Scan, Focus, and Amplify toward Guidance-aware Answering for Video TextVQA](https://mlsanity.com/paper/2511.20190/) (2025) - [NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior](https://mlsanity.com/paper/2504.00410/) (2025) - [TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance](https://mlsanity.com/paper/2505.23119/) (2025) - [DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2603.14207/) (2026) - [Dynamic Frequency Modulation for Controllable Text-driven Image Generation](https://mlsanity.com/paper/2602.10662/) (2026) ## Abstract (arXiv) The goal of scene text image super-resolution is to reconstruct high-resolution text-line images from unrecognizable low-resolution inputs. The existing methods relying on the optimization of pixel-level loss tend to yield text edges that exhibit a notable degree of blurring, thereby exerting a substantial impact on both the readability and recognizability of the text. To address these issues, we propose TextDiff, the first diffusion-based framework tailored for scene text image super-resolution. It contains two modules: the Text Enhancement Module (TEM) and the Mask-Guided Residual Diffusion Module (MRD). The TEM generates an initial deblurred text image and a mask that encodes the spatial location of the text. The MRD is responsible for effectively sharpening the text edge by modeling the residuals between the ground-truth images and the initial deblurred images. Extensive experiments demonstrate that our TextDiff achieves state-of-the-art (SOTA) performance on public benchmark datasets and can improve the readability of scene text images. Moreover, our proposed MRD module is plug-and-play that effectively sharpens the text edges produced by SOTA methods. This enhancement not only improves the readability and recognizability of the results generated by SOTA methods but also does not require any additional joint training. Available Codes:https://github.com/Lenubolim/TextDiff.