mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
- 38k
- C++
- Apache-2.0
- 2 h ago
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.
Web Augmented Reality. Image Tracking, Face Tracking. Tensorflow.js
JS Expert Week 7.0 - 🙅🤏🏻 Controlling Streaming Platforms using Eye and Hand Detection 👁🖐
XR Animator, AI-based Full Body Motion Capture and Extended Reality (XR) solution, powered by System Animator Online
Faking your webcam background under GNU/Linux, now supports background blurring, animated background, colour map effect, hologram effect and on-demand processing.
An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources.
This is a Computer vision package that makes its easy to run Image processing and AI functions. At the core it uses OpenCV and Mediapipe libraries.
Virtually controlling computer using hand-gestures and voice commands. Using MediaPipe, OpenCV Python.
Real-time portrait segmentation for mobile devices
On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.
🎬 Ultimate AI Auto-Clipper - Transform long-form videos & podcasts into viral shorts! Features smart face-tracking, kinetic karaoke subtitles, contextual B-roll, AI voice-overs, and auto-uploaders (YouTube/FB). Powered by Whisper, Gemini, MediaPipe, & Pyannote.
Connecting openFrameworks to Google MediaPipe Machine Learning Framework over UDP
从单张图片制作可动形象:本地运行的 2D 虚拟形象编辑器,分层绑定 / 网格形变 / 口型与眨眼 / 时间轴动效 / MediaPipe 实时驱动 / OBS 输出,内置大肥鱼1号示例工程。
Create and control 3D shapes using hand gestures in real-time. Built with mediapipe computer vision and threejs
19 ready-to-run computer vision projects with YOLO, ByteTrack & MediaPipe — counting, safety, ANPR, heatmaps and more
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.
Prebuilt binary for TensorFlowLite's standalone installer. For RaspberryPi. A very lightweight installer. I provide a FlexDelegate, MediaPipe Custom OP and XNNPACK enabled binary.
Control 3D models using hand gestures and voice commands in real-time. Threejs / mediapipe computer vision
🎥🤟 8 minimalistic templates for tfjs mediapipe handpose and facemesh
On-device customizable face recognition in Android with FaceNet and an embedded vector database
A threejs / WebGL / MediaPipe-powered interactive demo that allows you to control a 3D sphere using hand gestures.
Examples from my video about recognizing multiple hand gestures with tensorflowjs and fingerpose
Hand-controlled arpeggiator, drum machine, and audio reactive visualizer. Built with mediapipe computer vision, threejs, tonejs
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!
Modular, config-driven pipeline for preprocessing Sign Language datasets with pose and video outputs using MediaPipe, MMPose, and YOLO..
Animate shapes with hand gestures. Web tool built with threejs and mediapipe hand-tracking
Project for face detection, face recognition, pencil sketch, animegan in image, video or real-time stream
A Vtuber web app powered by the latest and great in motion capture tech from MediaPipe.
AirFlow - Gesture based air canvas using Machine Learning and Computer Vision.
Real-time webcam-driven anatomical visualization with interactive X-ray simulations of cranial, neural, and muscular structures.
Fly a 3D spaceship with your hand in the browser
Runs in the browser on Hugging Face