charliegerard/splat

Motion-controlled Fruit Ninja clone using Three.js & Tensorflow.js

33
/ 100
Emerging

Uses PoseNet for real-time pose estimation to track hand movements via webcam, enabling gesture-based fruit slicing without controllers. Built on Three.js for 3D rendering and physics simulation, with TensorFlow.js handling the ML inference entirely in-browser. The architecture leverages pose keypoints to detect cutting trajectories, demonstrating practical integration of computer vision with interactive 3D graphics.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

99

Forks

15

Language

JavaScript

License

Last pushed

Jun 24, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/charliegerard/splat"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.