#14 · Primary category: Computer Vision

mediapipe

android audio-processing c-plus-plus calculator computer-vision deep-learning framework graph-based graph-framework inference machine-learning mediapipe mobile-development perception pipeline-framework stream-processing video-processing

Cross-platform, customizable ML solutions for live and streaming media.

Project last updated:08/29/26

GitHub Stars

36.8K

Forks

6.1K

Contributors

114

License

Apache-2.0

Why we included this project

MediaPipe is the toolkit most teams reach for when they need camera-based perception on phones, browsers, or edge hardware. It ships ready-to-run solutions for hand and pose tracking, face landmarks, object detection, and segmentation behind small cross-platform APIs for Android, iOS, web, and Python. Below those high-level tasks sits a graph framework where you wire calculators into custom pipelines, so you can start from a working solution and swap in models trained on your own data. Because inference runs on the device, frames never leave it, which matters for latency-sensitive and privacy-conscious applications. Whether you want a quick gesture recognizer in a mobile app or a fully custom streaming pipeline for a desktop or IoT product, it is a practical fit.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category