ZZZHANG-jx

DocHighlight. [PRCV 25] Towards Real-World Document Specular Highlight Removal: The DocHighlight Dataset and DocSHRNet Method

sub2api. Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

claude-relay-service. CRS-自建Claude Code镜像，一站式开源中转服务，让 Claude、OpenAI、Gemini、Droid 订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

UniHIR. [ACL 2026 main] The official GitHub page of "Draft, Verify, Restore: Self-Refining Historical Inscription Restoration with a Unified MLLM"

Awesome-Generate-AI-for-Photography. Awesome List for Generative Models and Photography

ruankao. 软考达人 - 最新最全免费的软考题库。 高级：系统架构设计师、系统分析师、信息系统项目管理师、系统规划与管理师、网络规划设计师。 中级：软件设计师、网络工程师、系统集成项目管理工程师、数据库系统工程师、信息安全工程师、信息系统管理工程师、信息系统监理师、软件评测师、嵌入式系统设计师、电子商务设计师、多媒体应用设计师。 初级：信息系统运行管理员、信息处理技术员、网络管理员、程序员。

VisuRiddles. VisuRiddles: Fine-grained Perception is a important thing for Multimodal Large Models in Riddles Solving

minimalRL. Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

top-cvpr-2026-papers. About This repository is a curated collection of the most exciting and influential CVPR 2026 papers. 🔥 [Paper + Code + Demo]

VoxCPM. VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

opendataloader-pdf. PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

awesome-3d-datasets. [CVPRW'26] A collection and survey of 3d dataset

daily_stock_analysis. LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.

supertonic. Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Awesome-Streaming-Video-Understanding. 🔥🔥🔥 [Awesome] Latest Papers, Codes & Datasets on Streaming / Online Video Understanding — Building Always-on, Real-time Video AI 🤖

hello-agents. 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

Spider_XHS. 小红书爬虫数据采集，小红书全域运营解决方案

xhs. 基于小红书 Web 端进行的请求封装。https://reajason.github.io/xhs/

nanobot. Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

MiroFish. A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

edict. 🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

MobileAgent. Mobile-Agent: The Powerful GUI Agent Family

AgentCPM-GUI. AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.

landlord. 斗地主

ddz_game. 斗地主游戏

DouyinLiveRecorder. 可循环值守和多人录制的直播录制软件，支持抖音、TikTok、Youtube、快手、虎牙、斗鱼、B站、小红书、pandatv、sooplive、flextv、popkontv、twitcasting、winktv、百度、微博、酷狗、17Live、Twitch、Acfun、CHZZK、shopee等40+平台直播录制

rlcard. Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

TrendRadar. ⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

RoMaV2. Python

DeepSeek-OCR. Contexts Optical Compression

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Awesome-GUI-Agents. A curated collection of resources, tools, and frameworks for developing GUI Agents.

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

ForCenNet.

QT-TextSR. This repository is the implementation of "QT-TextSR: Enhancing scene text image super-resolution via efficient interaction with text recognition using a Query-aware Transformer", Neurocomputing 2024..

Dolphin. The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

WildDoc. The official repo for “WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?“

DocAligner-Distortion. [PRL 2025] Enhancing Document Dewarping Evaluation: A New Metric with Improved Accuracy and Efficiency

OCR-Reasoning. [ICLR 2026] OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning

AutoScaler. [PR 2026] The official GitHub page of "AutoScaler: Self Scale Alignment for Handwritten Mathematical Expression Recognition"

TokenFD. [ICCV2025] A Token-level Text Image Foundation Model for Document Understanding

DocSAM. Python

Awesome-Generative-Models-for-OCR. [arXiv 25] OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities

M6Doc.

PromptDA. [CVPR 2025] Prompt Depth Anything

DocLayLLM. [CVPR 2025] DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

LGGPT. [IJCV 2025] Smaller But Better: Unifying Layout Generation with Smaller Large Language Models

worth-calculator. Calculating the actual value of your job beyond just salary

cherry-studio. AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

RedundancyLens. Python

DocDewarpHV. Python

RWMD_dataset. The Real-world Mobile Document (RWMD) Database

FastV. [ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

AnimatedDrawings. Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

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

HDR. [AAAI2025 Oral] Predicting the Original Appearance of Damaged Historical Documents

PDFMathTranslate. [EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

DocKylin. [AAAI 2025] DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming

docling. Get your documents ready for gen AI

CTRNet-plus. The official implement of CTRNet++.

doc-matcher. Inference, training and evaluation code for our paper "DocMatcher: Document Image Dewarping via Structural and Textual Line Matching" (WACV) 2025.

TextHarmony. The official code for NeurIPS 2024 paper: Harmonizing Visual Text Comprehension and Generation

samurai. Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

TextHawk. Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models

Rectified-Diffusion. [ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need

inksight. Jupyter Notebook

VisualWebBench. Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"

LLM-Agent-Paper-List. The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

LLM_MultiAgents_Survey_Papers. Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)

UniMERNet. UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition

DTSM. Code and data for the paper: DTSM: Toward Dense Table Structure Recognition with Text Query Encoder and Adjacent Feature Aggregator

Show-o. [ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

HowToCook. Programmer's guide about how to cook at home.

ScaleDoc. Python

Campus2025. 2025届互联网校招信息汇总

DiffMatch. Official implementation of "Diffusion Model for Dense Matching" (ICLR'24 Oral)

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

Awesome-Chinese-LLM. 整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

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

KVP10k. Repository for the KVP10k dataset

M2Doc. Jupyter Notebook

TexTeller. TexTeller can convert image to latex formulas (image2latex, latex OCR) with higher accuracy and exhibits superior generalization ability, enabling it to cover most usage scenarios.

Bridging-Text-Spotting. (CVPR 2024) Bridging the Gap Between End-to-End and Two-Step Text Spotting.

TextCoT. [ACM TOMM] Official implementation of "TextCoT: Zoom-In for Enhanced Multimodal Text-Rich Image Understanding"

AI-on-the-edge-device. Easy to use device for connecting "old" measuring units (water, power, gas, ...) to the digital world

T-GATE. T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!

Draw-and-Understand. [ICLR2025] Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want

Recommendations-Document-Image-Processing. This repository contains a paper collection of the methods for document image processing, including appearance enhancement, deshadow, dewarping, deblur, and binarization.

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

RFUND. [MM'2024] Official release of RFUND introduced in the MM'2024 paper "PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction"

Visual-Text-Processing-survey. The official project of paper "Visual Text Processing: A Comprehensive Review and Unified Evaluation""

Awesome-LLMs-Datasets. Summarize existing representative LLMs text datasets.

DeepEraser. The official code for “DeepEraser: Deep Iterative Context Mining for Generic Text Eraser”, TMM, 2024.

Recommendations-Document-Image-Processing. This repository contains a paper collection of the methods for document image processing, including appearance enhancement, deshadowing, dewarping, deblurring, binarization and so on.

FontDiffuser. [AAAI2024] FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning

T-Rex. [ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

LLM-in-Vision. Recent LLM-based CV and related works. Welcome to comment/contribute!

Awesome-Deblurring. A curated list of resources for Image and Video Deblurring

GPT-4V_OCR. Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)

LA-DocFlatten. Code and Dataset for our paper: Layout-Aware Single-Image Document Flattening

illtrtemplate-model. Code from our paper "Template-guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction " (ICCVW) 2023.

GCDRNet. [TAI 2023] Appearance Enhancement for Camera-captured Document Images in the Wild

Document-Image-Dewarping. Python

Recommendations-Diffusion-Text-Image. A paper collection of recent diffusion models for text-image generation tasks, e,g., visual text generation, font generation, text removal, text image super resolution, text editing, handwritten generation, scene text recognition and scene text detection.

WMeter-Reader. [TIM 2025] Towards Accurate Readings of Water Meters by Eliminating Transition Error: New Dataset and Effective Solution

Mnist-99.7-Accuracy-with-Pytorch. A CNN model builds with Pytorch and reaches 99.7% accuracy

BGShadowNet. Python

DSRFGD. Document Shadow Removal with Foreground detection learning from Fully Synthetic Images

BoxDiff. [ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

Union14M. [ICCV 2023] Code base for Revisiting Scene Text Recognition: A Data Perspective

SMT. [ICCV2023] This is an official implementation for "Scale-Aware Modulation Meet Transformer".

DocAligner. [PR 2025] DocAligner: Automating the Annotation of Photographed Documents Through Real-virtual Alignment

augraphy. Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes

TabRecSet. A large scale camera-taken table detection and recognition dataset.

LATIN-Prompt. Python

VisorGPT. [NeurIPS 2023] Customize spatial layouts for conditional image synthesis models, e.g., ControlNet, using GPT

UDOP.

LLMsPracticalGuide. A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

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

Image2Paragraph. [Image 2 Text Para] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.

ColossalAI. Making large AI models cheaper, faster and more accessible

DocTr-Plus. The official code for “Deep Unrestricted Document Image Rectification”, TMM, 2023.

Awesome-Document-Image-Rectification. A comprehensive list of awesome document image rectification papers.

UDoc-GAN. Official PyTorch implementation for ACM MM22 "UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior"

layout-parser. A Unified Toolkit for Deep Learning Based Document Image Analysis

DocumentLayoutAnalysis. Document Layout Analysis resources repos for development with PdfPig.

TableMASTER-mmocr. 2nd solution of ICDAR 2021 Competition on Scientific Literature Parsing, Task B.

HorNet. [NeurIPS 2022] HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions

v2ray-core. A platform for building proxies to bypass network restrictions.

External-Attention-pytorch. 🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

Awesome-Image-based-Meter-Recognition-Reading.

free. 翻墙、免费翻墙、免费科学上网、免费节点、免费梯子、免费ss/v2ray/trojan节点、蓝灯、谷歌商店、翻墙梯子

Marior. [ACM MM 2022] Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild

yolov7. Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

LibtorchTutorials. This is a code repository for pytorch c++ (or libtorch) tutorial.

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

awesome-image-rectification. 📝 A curated list of image rectification papers.

deepfillv2. The PyTorch implementation of ICCV 2019 oral paper: free-form inpainting (deepfillv2), especially Gated Conv

SauvolaNet-torch. pytorch implement of SauvolaNet

Document_Binarization_Collection. This repository is a concise collection of well known deep learning based document binarization models.

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Awesome-Visual-Transformer. Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

labelbee-client. Out-of-the-box Annotation Toolbox

FocusOnDepth. A Monocular depth-estimation for in-the-wild AutoFocus application.

DocSegTr. A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers

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

sim2real-docs. Synthesize image datasets of documents in natural scenes with Python+Blender3D

BEDSR-Net_A_Deep_Shadow_Removal_Network_from_a_Single_Document_Image. Unofficial implementation of ''BEDSR-Net: A Deep Shadow Removal from a Single Document Image'' with PyTorch

DE-GAN-Implementation-Using-PyTorch. Document Enhancement Generative Adversarial Networks

DocTr. The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

torch-toolbox. 🛠 Toolbox to extend PyTorch functionalities

Deformable-Image-Registration-Projects. Deformable Image Registration Projects

Document-Dewarping-with-Control-Points. Document Dewarping with Control Points

FCN-for-Semantic-Segmentation. Implemention of FCN-8 and FCN-16 with Keras and uses CRF as post processing

DeOldify. A Deep Learning based project for colorizing and restoring old images (and video!)

Best_AI_paper_2020. A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code

pylsd-nova. Python bindings for Line Segment Detector (LSD)

document_warp. A script using OpenCV to perform perspective transforms on images of documents to give a head-on view.

waveCorrection. OCR Document image deformation correction.复现阿里OCR皱巴巴文档图像形变矫正

pytorch-deeplab-xception. DeepLab v3+ model in PyTorch. Support different backbones.

tps_stn_pytorch. PyTorch implementation of Spatial Transformer Network (STN) with Thin Plate Spline (TPS)

recursive-cnns. Implementation of the paper "Real-time Document Localization in Natural Images by Recursive Application of a CNN."

pytorch-wgan. Pytorch implementation of DCGAN, WGAN-CP, WGAN-GP

Document-Scanner. Python

Dewarping-Document-Image-By-Displacement-Flow-Estimation. Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network

BOOK-CONTENT-SEGMENTATION-AND-DEWARPING. Using FCN to segment the book's content and background, then dewarping the pages,

page_dewarp. Text page dewarping using a "cubic sheet" model

deep-learning-for-document-dewarping. An application of high resolution GANs to dewarp images of perturbed documents

Document-Image-Dewarping. Document Image Dewarping

SCUT-HCCDoc_Dataset_Release.

Object-Detection-Evaluation-Tool. Object Detection Evaluation Tools

simple-faster-rcnn-pytorch. A simplified implemention of Faster R-CNN that replicate performance from origin paper

DocIIW. Repository for Intrinsic Decomposition of Document Images In-the-Wild (BMVC '20)

RectiNet. A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping

EDSR-PyTorch. PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

Guided-Attention-Inference-Network. Contains implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018). This repository aims to apply GAIN on fcn8 architecture used for segmentation.

pytorch-auto-augment. PyTorch implementation of AutoAugment.

fast-autoaugment. Official Implementation of 'Fast AutoAugment' in PyTorch.

Unsupervised-Domain-Specific-Deblurring. Implementation of "Unsupervised Domain-Specific Deblurring via Disentangled Representations"

voxelmorph. Unsupervised Learning for Image Registration

network-slimming. Network Slimming (Pytorch) (ICCV 2017)

pytorch-slimming. Learning Efficient Convolutional Networks through Network Slimming, In ICCV 2017.

pytorch-ssim. pytorch structural similarity (SSIM) loss

pytorch-msssim. PyTorch differentiable Multi-Scale Structural Similarity (MS-SSIM) loss

conv_arithmetic. A technical report on convolution arithmetic in the context of deep learning

PyNET. Generating RGB photos from RAW image files with PyNET

crnn_ctc_ocr_tf. Extremely simple implement for CRNN by Tensorflow

tesseract. Tesseract Open Source OCR Engine (main repository)

pytorch-cnn-visualizations. Pytorch implementation of convolutional neural network visualization techniques

Pyramid-Attention-Networks-pytorch. Implementation of Pyramid Attention Networks for Semantic Segmentation.

CRAFT-pytorch. Official implementation of Character Region Awareness for Text Detection (CRAFT)

python-turtle-draw-svg. A python program for draw SVG file using turtle package.

gans-in-action. Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks

ocr-open-dataset. list all open dataset about ocr.

DeepLearning-500-questions. 深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

SRNet. A tensorflow reproducing of paper “Editing Text in the wild”

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

Image-Inpainting. A paper summary of image inpainting

the-gan-zoo. A list of all named GANs!