Repo AI đang lênCập nhật hằng ngày từ GitHub

A real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned

TextBoxes++: A Single-Shot Oriented Scene Text Detector

[ICRA 2025 Best Paper] MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry

Fork of tess-two rewritten from scratch to support latest version of Tesseract OCR.

ONNX Model Exporter for PaddlePaddle

An open source library for multiview geometry and structure from motion

[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

Open Source Visual Servoing Platform

Winner of Mozilla's $50,000 prize for AI

Search inside YouTube videos using natural language

:oncoming_automobile: "MORE THAN VEHICLE COUNTING!" This project provides prediction for speed, color and size of the vehicles with TensorFlow Object Counting API.

结束和新的开始

[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

Semi-Supervised Learning, Object Detection, ICCV2021

Hints, grids and vim keys for your whole desktop. Built for macOS, linux and windows, natively.

A Python wrapper for Tesseract and Cuneiform -- Moved to Gnome's Gitlab

An immersion toolkit for learning Languages through games and other visual media.

A Kitti Road Segmentation model implemented in tensorflow.

Fast, accurate OCR with correctness assessment.

[ICLR2022] official implementation of UniFormer

A curated collection of iOS, ML, AR resources sprinkled with some UI additions

This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord

无人驾驶的资源列表中文版

PDF to markdown using vision LLMs — tables, layouts, and structure preserved

[NeurIPS 2021] You Only Look at One Sequence

About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]

Computer Vision in Python

An local, offline (after initial setup), portable OCR software that can process images and PDF files, using DeepSeek-OCR-2 AI (running directly on your machine).

[CMU] A Versatile and Modular Framework Designed for Autonomous Unmanned Aerial Vehicles [UAVs] (C++/ROS/PX4)

Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation

JevChat-Windows：聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入，发送永远手动

Virtually controlling computer using hand-gestures and voice commands. Using MediaPipe, OpenCV Python.

CVPR2023-Occupancy-Prediction-Challenge

KeyForge3D is an app that turns a photo of a key into a 3D-printable STL file. Ideal for locksmiths and hobbyists, it analyzes the key's bitting pattern using image processing and generates an accurate 3D model for quick replication.

Implementation of YOLO v3 object detector in Tensorflow (TF-Slim)

本地监控 + AI 视觉 — LAN-based smartphone-powered AI monitoring framework with structured event output for data acquisition and analysis.

Note Companion: AI assistant for Obsidian that goes beyond just a chat. (prev File Organizer 2000)

A lightweight macOS selection translator built with pure Swift 6, featuring on-device Apple Translate for privacy, only 5MB install size and stable ~50MB memory usage. 一款轻量级 macOS 划词翻译工具，纯 Swift 6 开发，设备端 Apple 翻译保护隐私，安装体积仅 5MB，后台运行内存稳定约 50MB

Python Computer Vision & Video Analytics Framework With Batteries Included

A caffe implementation of MobileNet-YOLO detection network

A (very) simple UI lib built on top of OpenCV drawing primitives

Fast Automatic License Plate Recognition (ALPR) framework.

:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler

Darknet/YOLO object detection framework

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

A supermarket receipt parser written in Python using tesseract OCR

YoloDotNet - A C# .NET 8.0 project for Classification, Object Detection, OBB Detection, Segmentation and Pose Estimation in both images and live video streams.

An open-source computer vision framework to build and deploy apps in minutes

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.