Code for the paper "UVDoc: Neural Grid-based Document Unwarping" - Dataset capture and creation

Code for the paper "UVDoc: Neural Grid-based Document Unwarping"

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

A python wrapper for the Doc2X API and comes with native texts processing (to improve PDF recall in RAG). | Doc2X API的python封装，同时附带本地的文本处理(提升PDF在RAG中的召回率)。

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Handwritten Text Recognition and Character Detection

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

Query and Summarize your chat messages.

PPOCRLabelv2 is a semi-automatic graphic annotation tool suitable for OCR field, with built-in PP-OCR model to automatically detect and re-recognize data.

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

This repository is the official implementation of Disentangling Writer and Character Styles for Handwriting Generation (CVPR 2023)

Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.

Official implementation of UPOCR: Towards unified pixel-level OCR interface (ICML 2024)

一个能够在本地共享Plus账号，避免OpenAI标记降智前提下，使用原生网页版ChatGPT Plus的项目

Official implementation of PageNet (IJCV 2022)

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

Deep Face Recognition UI With ReactJS

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

Vision model based document ingestion

[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

OpenOCR: A general OCR system with accuracy and efficiency. Supporting 24 Scene Text Recognition methods trained from scratch on large-scale real datasets, and will continue to add the latest methods.

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。