MediaPipeのPythonパッケージのサンプルです。2024/9/1時点でPython実装のある15機能について用意しています。

Google MediaPipe Face + Hands + Body + Object

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.

[ECCV 2024] PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-view Self-Guidance

YOLOv5-OpenPose designed for CPU

Holistic end-to-end video detection and visualization of body pose, hands with fingers, and face mesh in both 2D overlay and 3D scene

Test MediaPipe Holistic JS Model

A computer vision Rock Paper Scissors game

A complete social media operator's playbook — 37 skills, 12 functions, any agent. Agent-agnostic skill graph for X, LinkedIn, IG, TikTok. Works with Hermes, Claude Code, Droid, Cursor, OpenAI agents. Built by Crewm8 (crewm8.ai).

Final project for the course of Human Robot Interaction and Reasoning Agents 2021/2022.

Cosmic-Ecommerce is a full-stack online store for spiritual and holistic products like yantras, pyramids, malas, and vastu items, built to support CosmicEnergies' mission of spreading positive energy and ancient wisdom.

A python class consisting of all mediapipe funciton

A banyan of all things PluralityNET — many roots, trunks, and interconnectedness folders at the top repository directory

Equusential Web Page. Webpage built for my small business. Providing equine myofunctional therapy and bit-fitting services to the Gippsland region.

This Android can be used to extract holistic landmark and based on google's Mediapipe

@encapsule/arctools package distribution contains command line tools and utilities based on @encapsule/arccore package runtime data modeling, routing, and analysis algorithms.

Application of MediaPipe Holistic pipeline that integrates integrates separate models for pose, face and hand components

A simple Python3 script. It uses mediapipe module to recognize the face of a user in real-time.

This code snippet uses MediaPipe's Holistic model to visualize pose estimation, hand, and face landmarks on images, videos, and live camera feed. It draws landmarks and body pose connections, focusing on facial contours, hand landmarks, and body posture. Result is displayed in a resizable window.