Awesome

Survey-of-Visual-Text-Processing

The official project of paper "Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing"

This repository contains a paper collection of recent works for visual text processing tasks.

📖 Table of Contents 👀

• Text Image Super-resolution
• Document Image Dewarping
• Text Image Denosing
• Scene Text Removal
• Scene Text Editing
• Scene Text Generation

Text Image Super-resolution

• Boosting Optical Character Recognition: A Super-Resolution Approach (2015 arxiv) paper
• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2017 CVPR) paper
• TextSR: Content-Aware Text Super-Resolution Guided by Recognition (2019 arxiv) paper code
• Selective Super-Resolution for Scene Text Images (2019 ICDAR) paper
• Text-Attentional Conditional Generative Adversarial Network for Super-Resolution of Text Images (2019 ICME) paper
• Collaborative Deep Learning for Super-Resolving Blurry Text Images (2020 TCI) paper
• PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution Unit (2020 ECCV) paper
• Scene Text Image Super-Resolution in the Wild (2020 ECCV) paper code
• Scene Text Telescope: Text-Focused Scene Image Super-Resolution (2021 CVPR) paper
• Scene Text Image Super-Resolution via Parallelly Contextual Attention Network (2021 CVPR) paper
• Text Prior Guided Scene Text Image Super-Resolution (2021 TIP) paper code
• A text attention network for spatial deformation robust scene text image super-resolution (2022 CVPR) paper code
• C3-STISR: Scene Text Image Super-resolution with Triple Clues (2022 IJCAI) [paper]
• Text gestalt: Stroke-aware scene text image super-resolution (2022 AAAI) paper code
• A Benchmark for Chinese-English Scene Text Image Super-Resolution (2023 ICCV) paper code
• Text Image Super-Resolution Guided by Text Structure and Embedding Priors (2023 ACM MM) paper
• Improving Scene Text Image Super-Resolution via Dual Prior Modulation Network (2023 AAAI) paper code
• Learning Generative Structure Prior for Blind Text Image Super-Resolution (2023 CVPR) paper code

Document Image Dewarping

• A Fast Page Outline Detection and Dewarping Method Based on Iterative Cut and Adaptive Coordinate Transform (2019 ICDARW) paper

• DocUNet: Document Image Unwarping via a Stacked U-Net （2018 CVPR）paper

• DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks (2019 ICCV) [paper code

• Document rectification and illumination correction using a patch-based CNN (2019 TOG) paper

• Dewarping Document Image by Displacement Flow Estimation with Fully Convolutional Network (2020 IAPR) paper

• Geometric rectification of document images using adversarial gated unwarping network (2020 PR) paper

• DocScanner: Robust Document Image Rectification with Progressive Learning (2021 arxiv) paper

• End-to-End Piece-Wise Unwarping of Document Images (2021 ICCV) paper

• Document Dewarping with Control Points (2021 ICDAR) paper paper

• DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction (2021 ACM MM) paper code

• Revisiting Document Image Dewarping by Grid Regularization (2022 CVPR) paper

• Fourier Document Restoration for Robust Document Dewarping and Recognition ((2022 CVPR) paper

• Learning an Isometric Surface Parameterization for Texture Unwrapping (2022 ECCV) paper code

• Geometric Representation Learning for Document Image Rectification (2022 ECCV) paper

• Learning From Documents in the Wild to Improve Document Unwarping (2022 SIGGRAPH) paper code

• Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild (2023 ACM MM) paper code

• DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures (2023 arxiv) paper

• DocMAE: Document Image Rectification via Self-supervised Representation Learning (2023 ICME*) paper

• Deep Unrestricted Document Image Rectification (2023 arxiv) paper code

• Layout-aware Single-image Document Flattening (2023 TOG) paper code

Text Image Denosing

• Shading Removal of Illustrated Documents (2013 ICDAR) paper
• Nonparametric illumination correction for scanned document images via convex hulls (2013 TPAMI) paper
• Removing shadows from images of documents (2016 ACCV) paper
• Document enhancement using visibility detection (2018 CVPR) paper
• Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removal (2018 ACCV) paper
• Learning to Clean: A GAN Perspective (2018 ACCVW) paper
• Deeperase: Weakly supervised ink artifact removal in document text images (2020 WACV) paper
• From Shadow Segmentation to Shadow Removal (2020 ECCV) paper
• BEDSR-Net: A Deep Shadow Removal Network From a Single Document Image (2020 CVPR) paper
• Light-Weight Document Image Cleanup Using Perceptual Loss (2021 ICDAR) paper
• RecycleNet: An Overlapped Text Instance Recovery Approach (2021 ACM MM) paper
• End-to-End Unsupervised Document Image Blind Denoising (2021 ICCV) paper
• Bijective mapping network for shadow removal (2022 CVPR) paper
• Style-guided shadow removal (2022 ECCV) paper code
• UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior (2022 ACM MM) paper code
• LP-IOANet: Efficient High Resolution Document Shadow Removal (2023 ICASSP) paper
• Shadow Removal of Text Document Images Using Background Estimation and Adaptive Text Enhancement (2023 ICASSP) paper
• Mask-Guided Stamp Erasure for Real Document Image (2023 ICME) paper
• Document Image Shadow Removal Guided by Color-Aware Background (2023 CVPR) paper
• DocDiff: Document Enhancement via Residual Diffusion Models (2023 ACM MM) paper code
• DocNLC: ADocument Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degradations (2024 AAAI) paper code

Scene Text Removal

• Image-to-Image Translation with Conditional Adversarial Networks^* (2017 CVPR) paper

• Scene text eraser (2017 ICDAR) paper

• Automatic Semantic Content Removal by Learning to Neglect (2018 BMVC) paper

• Ensnet: Ensconce text in the wild (2019 AAAI) paper code

• Mtrnet: A generic scene text eraser (2019 ICDAR) paper

• Erasenet: End-to-end text removal in the wild (2020 TIP) paper code

• Mtrnet++: One-stage mask-based scene text eraser (2020 CVIU) paper

• Erasing scene text with weak supervision (2020 WACV) paper

• Stroke-Based Scene Text Erasing Using Synthetic Data for Training (2021 TIP) paper

• Text region conditional generative adversarial network for text concealment in the wild (2021 TCSVT) paper

• Two-Stage Seamless Text Erasing On Real-World Scene Images (2021 ICIP) paper

• Scene text removal via cascaded text stroke detection and erasing (2022 CVM) paper

• Self-supervised text erasing with controllable image synthesis (2022 ACM MM) paper

• Multi-branch network with ensemble learning for text removal in the wild (2022 ACCV) paper

• The Surprisingly Straightforward Scene Text Removal Method with Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis (2022 ECCV) paper code

• Don’t forget me: accurate background recovery for text removal via modeling local-global context (2022 ECCV) paper code

• Psstrnet: progressive segmentation-guided scene text removal network (2022 ICME) paper

• Fetnet: Feature erasing and transferring network for scene text removal (2023 PR) paper

• Modeling stroke mask for end-to-end text erasing (2023 WACV) paper

• Viteraser: Harnessing the power of vision transformers for scene text removal with segmim pretraining (2023 arxiv) paper code

• Progressive scene text erasing with self-supervision (2023 CVIU) paper

• What is the Real Need for Scene Text Removal? Exploring the Background Integrity and Erasure Exhaustivity Properties (2023 TIP) paper code

• Selective scene text removal (2023 BMVC) paper code

Scene Text Editing

• Scene text magnifier (2019 ICDAR) paper
• Selective style transfer for text (2019 ICDAR) paper code
• Editing text in the wild (2019 ACM MM) paper code
• Swaptext: Image based texts transfer in scenes (2020 CVPR) paper
• Scene text transfer for cross-language (2021 ICIG) paper
• Mask-guided gan for robust text editing in the scene (2021 Neurocomputing) paper
• Stefann: scene text editor using font adaptive neural network (2020 CVPR) paper
• Deep learning-based forgery attack on document images (2021 TIP) paper
• Strive: Scene text replacement in videos (2021 ICCV) paper
• RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Styles (2022 CVPRW) paper code
• Fast: Font-agnostic scene text editing (2023 arxiv) paper
• Letter Embedding Guidance Diffusion Model for Scene Text Editing (2023 ICME) paper
• Exploring stroke-level modifications for scene text editing (2023 AAAI) paper code
• Textstylebrush: Transfer of text aesthetics from a single example (2023 TPAMI) paper
• Self-Supervised Cross-Language Scene Text Editing (2023 ACM MM) paper
• Scene style text editing (2023 arxiv) paper
• Improving Diffusion Models for Scene Text Editing with Dual Encoders (2023 arxiv) paper code
• Towards scene-text to scene-text translation (2023 arxiv) paper
• DiffUTE: Universal Text Editing Diffusion Model (2023 NIPS) paper code
• On manipulating scene text in the wild with diffusion models (2024 WACV) paper
• AnyText: Multilingual Visual Text Generation And Editing (2024 ICLR) paper code

Scene Text Generation

• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition (2014 arxiv) paper
• Synthetic data for text localisation in natural images (2016 CVPR) paper paper code
• Text detection in traffic informatory signs using synthetic data (2017 ICDAR) paper
• Verisimilar image synthesis for accurate detection and recognition of texts in scenes (2018 ECCV) paper code
• Spatial Fusion GAN for Image Synthesis (2019 CVPR) paper
• Learning to draw text in natural images with conditional adversarial networks (2019 IJCAI) paper
• ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation (2020 CVPR) paper
• SynthText3D: synthesizing scene text images from 3D virtual worlds (2020 Science China Information Sciences) paper
• UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World (2020 arxiv) paper code
• Synthtiger: Synthetic text image generator towards better text recognition models (2021 ICDAR) paper code
• Vector Quantized Diffusion Model for Text-to-Image Synthesis (2022 CVPR) paper
• Photorealistic text-to-image diffusion models with deep language understanding (2022 NIPS) paper
• eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers (2022 arxiv) paper code
• Character-Aware Models Improve Visual Text Rendering (2022 arxiv) paper
• Deepfloyd (2023) code
• GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation (2023 arxiv) paper code
• TextDiffuser: Diffusion Models as Text Painters (2023 NIPS) paper code
• Glyphcontrol: Glyph conditional control for visual text generation (2023 NIPS) paper code
• AnyText: Multilingual Visual Text Generation And Editing (2024 ICLR) paper code
• Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering (2024 ECCV) paper code

Cite

If you are interested in it, please star our project! And cite our paper as follows:

@article{shu2024visual,
  title={Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing},
  author={Shu, Yan and Zeng, Weichao and Li, Zhenhang and Zhao, Fangmin and Zhou, Yu},
  journal={arXiv preprint arXiv:2402.03082},
  year={2024}
}