GesturAR: An Authoring System for Creating Freehand Interactive Augmented Reality Applications
summary
GesturAR is an end-to-end authoring system that maps embodied freehand demonstrations to AR reactions using trigger-action visual programming, letting users scan, sketch or import models, demonstrate gestures, and immediately test interactions. Static poses use 10 joint angles compared by a Siamese network trained on 18 gestures; dynamic gestures become state lists of pose, hand velocity, and palm direction; synchronous gestures extract a numeric key (distance/angle/diameter), with 8 synchronous types implemented. The system produces interactive objects, robots, avatars and room-scale AR spaces and reports a user study of performance and usability.
AI-written summary · about
chapters (5)
related talks
16mPortal-ble: Intuitive Free-hand Manipulation in Unbounded Smartphone-based Augmented Reality
15mGhostAR: A Time-space Editor for Embodied Authoring of Human-Robot Collaborative Task with ...
16mMagicalHands: Mid-Air Hand Gestures for Animating in VR
33mDesigning AR Applications
14mImaginateAR: AI-Assisted In-Situ Authoring in Augmented Reality
09magentAR: Creating Augmented Reality Applications with Tool-Augmented LLM-based Autonomous Agents
20mToward Realistic Hands Gesture Interface: Keeping it Simple for Developers and Machines
15mVideo-Annotated Augmented Reality Assembly Tutorials