(eBook，PDFs Translation) A multilingual eBook processing tool supporting all eBook formats. Features online and offline translation while preserving original layouts. Compatible with both scanned a…

Get up and running with Llama 3, Mistral, Gemma, and other large language models.by adding more amd gpu support.

OCR, layout analysis, reading order, table recognition in 90+ languages

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

ROCm Library Files for gfx1103 and update with others arches based on AMD GPUs for use in Windows.

This is a simple text image blind super-resolution model, using BSRGAN

Learning Generative Structure Prior for Blind Text Image Super-resolution [CVPR 2023]

[CVPR2024] Diffusion-based Blind Text Image Super-Resolution (Official)

Official Code for 'C3-STISR: Scene Text Image Super-resolution with Triple Clues' - IJCAI 2022

A collection of papers and resources on scene text image super-resolution.

A toolbox of scene text super-resolution and recognition

ACM Multimedia 2023: DocDiff: Document Enhancement via Residual Diffusion Models. Also contains 1597 red seals in Chinese scenes, along with their corresponding binary masks.

Official code for DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degradations (AAAI 2024)

DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022

ClearText is an AI-powered text detection and enhancement tool that helps make text in images more readable and clearer. Perfect for improving the legibility of text in scanned documents, photos, a…

A comprehensive list of awesome document image rectification papers.

[CVPR 2024] DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks

《美国反对美国》是王沪宁先生在上世纪80年代末赴美观察写作的。我们知道在那个年代中国对西方特别是美国的追捧有多高，所以突然看到一个学者在80年代就有如此清楚的认识，十分钦佩。由于网上只有效果很差的PDF扫描版，所以我想利用OCR技术和肉眼（人体OCR）来转成现代化的文本格式。目前已经全部完成。

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

收货地址智能解析 Written in Go，可识别出：姓名+电话+邮编+身份证号+省+市+区+街道地址 超高性能（一条仅需 0.0000625s）

纯PHP版，收货地址智能解析，不需要数据库支持，简单易用。可解析（身份证号，电话，座机，区号，拆分省+市+区+街道地址）

A smart USB drive for Tesla Dashcam - extended storage, auto archive, web viewer

intelephense (PHP language server) extension for coc.nvim. intelephense’s various LSP features and this extension's additional features are available.

提供同花顺客户端/miniqmt/雪球的股票量化交易，支持跟踪 joinquant /ricequant 模拟交易 和 实盘雪球组合

区块链的构造和解释（structure-and-interpretation-of-blockchain）

采集和分析沪深股票财务数据

A fast PostgreSQL Database Client Library for Python/asyncio.