#Mediapipe
Showing 52 of 52 repositories tagged #mediapipe, ranked by stars
Cross-platform, customizable ML solutions for live and streaming media.
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
JS Expert Week 7.0 - 🙅🤏🏻 Controlling Streaming Platforms using Eye and Hand Detection 👁🖐
Lazyeat（懒人手势）｜手势隔空控制，比划就行！Lazyeat is a touch-free controller for use while eating! Don't want greasy hands while watching shows or browsing the web during meals? You can pause videos/full screen/switch videos just by gesturing to the camera!
An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources.
TensorFlow Lite Samples on Unity
Virtually controlling computer using hand-gestures and voice commands. Using MediaPipe, OpenCV Python.
MediaPipe(Python版)を用いて手の姿勢推定を行い、検出したキーポイントを用いて、簡易なMLPでハンドサインとフィンガージェスチャーを認識するサンプルプログラムです。（Estimate hand pose using MediaPipe(Python version). This is a sample program that recognizes hand signs and finger gestures with a simple MLP using the detected key points.）
Virtual Video Device for Background Replacement with Deep Semantic Segmentation
Real-time portrait segmentation for mobile devices
Real-time MMD motion capture on Web
Demo on adding virtual background to a live video stream in the browser
PennyWise automatically reads transaction SMS messages and transforms them into organized financial data with on-device AI assistance. No manual entry, no cloud processing, complete privacy.
这是一个 Flutter Packge 以实现摄像头精确追踪并识别十指的运动路径/轨迹和手势动作, 且输出22个手部关键点以支持更多手势自定义. 基于这个包可以编写业务逻辑将手势信息实时转化为指令信息: 一二三四五, rock, spiderman...还可以对不同手势编写不同特效. 可用于短视频直播特效, 智能硬件等领域, 为人机互动带来更自然丰富的体验
Human action classification system with pose-based (MediaPipe) and video-based (3D CNN) models. Features 100+ architectures for real-time pose classification and temporal models pretrained on UCF-101/HMDB51.
Create and control 3D shapes using hand gestures in real-time. Built with mediapipe computer vision and threejs
BlazePoseBarracuda is a human 2D/3D pose estimation neural network that runs the Mediapipe Pose (BlazePose) pipeline on the Unity Barracuda with GPU.
HolisticMotionCapture is an application and package that can capture the motion of a person with only a monocular color camera and move the VRM avatar's pose, face, and hands.
HolisticBarracuda is the Unity Package that simultaneously estimates 33 pose, 21 per-hand, and 468 facial landmarks on the Unity Barracuda with GPU.
Local-first AI photo culling for professional photographers — 6-axis rubric, XMP/IPTC export, Lightroom & Capture One ready.
Open-source webcam head tracking for iRacing. Achieve VR-style POV with any standard webcam!
Developed an AI-based system to control the mouse cursor using Python and OpenCV with the real-time camera. Fingertip location is mapped to RGB images to control the mouse cursor.
🎯 AirControl - 隔空手势+语音控制系统 | Gesture + Voice Control System for Windows
Control OpenLayers, Google Maps, and Leaflet with hand gestures via webcam. Uses MediaPipe for real time hand tracking to pan, zoom, and navigate maps hands free in the browser. No backend required.
Full body pose estimation to be used with HMD (Quest2) built in Unity
Motion capture for the character models of Honkai: Star Rail base on Unity and MediaPipe. Currently face only. (Do not need an iPhone)
Neural Network that is able to translate any sign language into text.
Real time webcam face detection, protect yourself from COVID19 with a virtual mask
SafeDriveVision is a computer vision project aimed at enhancing road safety. This project leverages deep learning models to detect and alert in real-time the dangerous behaviors of drivers, such as using a phone while driving or showing signs of drowsiness.
Realtime Face Effects in Browser using mediapipe and three js.
Deep Learning and Computer Vision Applications using Streamlit
Simulate mouse input using hand tracking
Real-time eye, facial-landmark, head-pose, blink, and gaze tracking for aviation human factors and HCI
Transform facial images with virtual makeup using Python, OpenCV, and MediaPipe. This script enables real-time application of lipstick, eye shadow, eyebrow color, and eyeliner based on facial landmarks. Ideal for experimenting with different makeup styles using video, image, or live camera inputs.
In this project we will be using the live feed coming from the webcam to create a virtual mouse with complete functionalities.
C API for Google's MediaPipe framework
A website that recognizes human sign language and translates it into text.
The purpose of this project is to detect the squat angles which will be helpful for the fitness instructors to provide corrective advice where appropriate.
Computer Vision Helping Library
SelfieSegmentationBarracuda is a human segmentation neural network that runs the Mediapipe Selfie Segmentation on the Unity Barracuda.
Spatial prompt engineering through interactive 3D concept graphs
This repository contains code for collecting pose data of various yoga poses using the MediaPipe Pose model. The collected data includes the angles of different body joints in each yoga pose.
Improved ReferenceLatent for ComfyUI — per-image strength, timestep gating, MediaPipe auto-masks, 1-4 image inputs. Works with Flux, Klein, Lumina, Wan, Hunyuan, Qwen-Image.
ComfyUI node for WAN I2V control with built-in person/face mask generation using MediaPipe
Engineered an AI model utilizing advanced Computer Vision and Google Generative AI to solve math problems by recognizing hand gestures, offering real-time, accurate solutions through an intuitive interface inspired by Apple Tablet calculators.
An Android App recreating the Simon Says game. Uses MediaPipe to run an LLM on device
Android-based AI-powered sports assistant
Image Classification, Image Captioning and LLM inference with LiteRT
A real-time, hand-controlled 3D particle physics engine built with Three.js and MediaPipe. Architected entirely by Google Gemini 3.0 via prompt engineering in under 59.3 seconds.
Machine learning and computer vision project that can interpret ASL