Royalvice / DocDiff
ACM Multimedia 2023: DocDiff: Document Enhancement via Residual Diffusion Models. Also contains 1597 red seals in Chinese scenes, along with their corresponding binary masks.
☆265Updated 7 months ago
Alternatives and similar repositories for DocDiff:
Users that are interested in DocDiff are comparing it to the libraries listed below
- This repository contains a paper collection of the methods for document image processing, including appearance enhancement, deshadowing, …☆227Updated last month
- Official code for DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degra…☆27Updated 4 months ago
- NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document Enhancement☆42Updated 7 months ago
- [CVPR2024] Diffusion-based Blind Text Image Super-Resolution (Official)☆123Updated last week
- [TAI 2023] Appearance Enhancement for Camera-captured Document Images in the Wild☆35Updated last year
- Code for the paper "UVDoc: Neural Grid-based Document Unwarping"☆128Updated 7 months ago
- ☆50Updated last year
- Learning Generative Structure Prior for Blind Text Image Super-resolution [CVPR 2023]☆223Updated this week
- The official project of paper "Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing"☆59Updated 2 months ago
- This repository is the implementation of "Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Contex…☆86Updated 2 years ago
- Official implementation of UPOCR: Towards unified pixel-level OCR interface (ICML 2024)☆49Updated 9 months ago
- Official implementation of ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining (AAAI 20…☆49Updated 8 months ago
- ☆34Updated last year
- [IJCAI2023] Your text images can be more clearer!☆56Updated last year
- The code and the DIW dataset for "Learning From Documents in the Wild to Improve Document Unwarping" (SIGGRAPH 2022)☆128Updated 7 months ago
- DocTr++ in PaddlePaddle☆48Updated 8 months ago
- [AAAI2025 Oral] Predicting the Original Appearance of Damaged Historical Documents☆68Updated last week
- A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022)☆172Updated 2 years ago
- ☆119Updated last year
- Real-CE: A Benchmark for Chinese-English Scene Text Image Super-resolution (ICCV2023)☆84Updated last year
- The official repo for [CVPR'23] "DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting" & [ArXiv'23] "DeepSolo++:…☆263Updated 7 months ago
- The official code for “Geometric Representation Learning for Document Image Rectification”, ECCV, 2022.☆80Updated last month
- [ICCV 2023] Code base for Revisiting Scene Text Recognition: A Data Perspective☆186Updated last year
- DocBank 文档图像增强数据集，此数据集用于文档图像增强，具体任务包括以下内容：Seal detection & Removal 印章检测 & 移除 ；Watermark detection & Removal 水印检测 & 移除；Document deblurrin…☆24Updated 5 months ago
- ☆172Updated last year
- The official code for “Deep Unrestricted Document Image Rectification”, TMM, 2023.☆433Updated 4 months ago
- Document Image Enhancement with GANs - TPAMI journal☆196Updated 2 years ago
- The official implementation of SPTS v2: Single-Point Text Spotting☆131Updated last year
- Scene text removal via cascaded text stroke detection and erasing☆32Updated 2 years ago
- [CVPR 2024] DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks☆401Updated 2 months ago